customer service teams

Abstract: As Large Language Model (LLM) agents increasingly participate in persistent social environments, understanding their long-term social interaction capabilities becomes increasingly important. While existing research has advanced long-term memory and conversational context retrieval, less attention has been paid to whether agents can autonomously re-engage with previously inactive conversations. In particular, remembering a past interaction does not necessarily mean that an agent can identify when to revisit it, decide to return, or reconstruct the context needed for a coherent continuation. To investigate this gap, we introduce agent social re-entry as a multi- dimensional evaluation problem, distinguishing three complementary capabilities: Finding, Returning, and Reconstructing. We develop a shared-snapshot evaluation framework that measures these dimensions independently, allowing us to examine how conversational resurfacing and persistent memory relate to different aspects of social re-entry. Evaluations across six LLM configurations show that resurfacing substantially improves target conversation identification, while persistent memory is associated with higher rates of autonomous target-directed replying. However, neither improvement is accompanied by consistent gains in contextual reconstruction. These results highlight the distinction between accessing previous conversations, choosing to re-engage, and maintaining conversational continuity. Our framework provides a way to evaluate these capabilities separately rather than relying on memory retrieval or conversational response quality alone.

Abstract: Agents built on large language models are increasingly allowed to take consequential actions: cancelling bookings, issuing refunds, changing accounts. The rules that govern those actions, such as "obtain the customer's explicit confirmation before changing anything", are usually stated in the prompt and followed only as reliably as the model chooses to follow them. We present Concordat, a Python library that treats an agent as an object whose interface is a finite-state protocol, in the spirit of typestate and session types, and enforces that protocol on the model at run time. On every turn the model is offered only the tools that are legal in the current protocol state, calls outside that set are rejected before they have side effects, decisions reserved for humans can only be requested, and token and tool-call budgets are charged and split linearly across handoffs. Protocols are checked when they are defined, and a subclass of an agent is rejected if it could bypass its parent's protocol, a behavioural form of Liskov substitution. We evaluate a Concordat agent against the standard agent of tau-bench on its 50 airline tasks, adding simulated customers who pressure the agent to skip confirmation. The standard agent made changes without the required "yes" in 13 of 50 tasks with gpt-4.1 and in 29 of 128 task-runs with Claude Haiku 5.5; the Concordat agent made none, with no significant difference in task success. tau-bench's own reward did not detect most of these violations. Concordat is open source.

Abstract: We describe the agent we submitted to the GLEE Competition, which plays bargaining, negotiation, and persuasion games against a shared pool of human and AI opponents. The agent is built around three central components: a classical game-theoretic solver to compute numeric moves, an online Bayesian layer to estimate opponent archetypes, and a language model to write accompanying messages. We utilize Rubinstein bargaining for bargaining, Faratin concession for negotiation, and Kamenica--Gentzkow disclosure for persuasion, and adapt those models to live opponents using two separate layers: a Bayesian estimate of the opponent's hidden discount factor, reservation value, or signaling reliability, and a Thompson sampling bandit over five moral-foundation framings coupled with an evidence-intuition spectrum to establish message register. Most of the development effort went into the recurring problem that theoretically optimal policies perform poorly in certain live settings; we report associated failure modes, guardrails we built, and our hypotheses. We additionally evaluate our model over 13,200 Monte Carlo games against 11 synthetic opponent archetypes, an ablation of the opponent-modeling layer, and an extensive analysis of 9,337 live-game messages in which moral rhetoric framing in the persuasion setting is strongly correlated with whether the buyer purchased ($χ^2=616.7$, $p \approx 3.7\times10^{-132}$), surviving controls for quality, round, and configuration.

Abstract: Web systems increasingly predict users' decisions from what users say, yet when interests partly conflict, users may promise to cooperate to win the other side's cooperation and then not do so. Sales or service agents that rely on such promises may grant concessions to users who then do not keep their promises, at a cost to the party they represent. We test how LLMs combine users' statements with decision records to predict users' decisions, using 1,260 rounds in which 42 users played a repeated prisoner's dilemma-style game with five agents, each prompted to express a dominant Big Five trait, and could talk with the agent before every decision. Across eight open-weight LLMs, predictions from decision records separated cooperation from defection well (AUC = .80), and adding dialogue brought no detectable gain. With dialogue, predictions agreed with users' statements more often, and errors concentrated on rounds in which users broke their statements: accuracy on rounds with a statement barely changed (.73 to .74), while it rose on kept statements (.76 to .95) and fell sharply on broken ones (.65 to .17). Predictions weighted statements more heavily than users' behavior warranted: when users stated a decision they had not yet made in that game, the predicted probability of keeping it rose from .13 to .69, whereas users kept .40 of such statements. Users' decisions also varied with the agent they faced, but predictions hardly reflected this: users cooperated more with the Agreeableness agent than with the Extraversion agent (70.6% vs. 54.5%), whereas predicted cooperation was nearly identical (64.5% vs. 63.1%). Users also cooperated more with an agent when they themselves scored higher on that agent's trait, whereas predicted cooperation barely changed with these scores. Dialogue-based predictions should therefore weigh users' statements by their earlier decisions and the agent they face.

Abstract: As agents collaborate on longer tasks, responsibility may pass between models before the work is complete. The receiving model must build on prior decisions, observations, and actions while addressing the remaining requirements. Evaluating this transition requires connecting the information preserved at handoff to how the receiver continues the work, a relationship that task-success and memory-retention scores alone do not capture. We introduce the Handoff State Continuity Benchmark (HSC-Bench), comprising 1,039 tasks that evaluate two complementary aspects of task takeover: recovering relevant repository evidence and continuing from established conversational, tool, and file-work state. Comparisons across six receiving models show that structured handoff state improves repository evidence recovery for every model and continuation performance for most models. The strongest receivers differ between the two tracks, showing that evidence-recovery rankings alone do not characterize performance when continuing from inherited state. By combining these comparisons with checks of subsequent responses and actions, HSC-Bench evaluates both access to prior evidence and adherence to established commitments and completed work. This provides a basis for selecting receiving models and assessing handoff representations according to the work that must be carried forward.

Abstract: Direct messaging is often employed by social media content creators to directly interact with followers. Those creators attempt to engage with followers in private communication, but they often encounter a large volume of messages. Through formative interviews with 15 creators, we found that creators frequently experience fatigue from writing suitable content, as they moderate audience expectations while concurrently integrating their media personas into responses. To explore how AI can address these challenges, we designed a system providing personalized, AI-generated response suggestions tailored to creators' writing styles to maintain their media personas. In a comparison study with 13 creators that examines how the system affects response behaviors, creators valued the system's ability to soften potential impoliteness and anticipated higher response rates, helping them maintain a professional image. However, creators reported additional labor in verifying the authenticity of AI outputs to mitigate risks caused by AI misalignment. Our results indicate that while AI suggestions enhance efficiency, they can undermine a creator's engagement in communication by shifting their attention toward monitoring AI.

Abstract: Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer. Existing evaluations assess memory capabilities without directly establishing whether memory use benefits the user. To study this gap, we collect approximately 1,000 pairwise judgments from 87 participants using their own ChatGPT queries and personal memories. We find that memory-conditioned responses are not consistently preferred over responses generated without memory and in some cases, users strongly prefer the latter. Automatic evaluators also show limited agreement with users and favor memory-conditioned responses substantially more often than users do. Motivated by these gaps, we introduce a memory-aware reward model that learns from user judgments, achieving 72.8\% preference prediction accuracy and outperforming the existing baselines. Our findings motivate evaluation and optimization objectives that align memory use with the preferences of the people whose information is being used.

Abstract: Sycophancy, where an LLM becomes overly agreeable, deferential, or flattering toward the user, has been identified as a major failure mode. While post-training has been implicated as a cause, how it internally gives rise to sycophantic behavior remains insufficiently understood. Post-training transforms the model's output from text completion into utterances directed toward an addressee, thereby giving the output \textit{addressivity}. We hypothesize that the accompanying pressure to follow the addressee's instructions and align with their preferences links this addressivity to sycophancy. To test this, we use Sparse Autoencoders to extract addressivity directions from pre-trained and post-trained models and examine their relationship with sycophancy. Steering models with addressivity directions can amplify or suppress sycophancy, and this effect is observed only in post-trained models. Furthermore, comparing the internal mechanisms of both model types confirms that the association between addressivity and sycophancy is strengthened through post-training. Finally, through a controlled post-training experiment, we find that models are sycophantic not toward a specific addressee but toward any recognized addressee, suggesting that the presence of an addressee, rather than the addressee's identity, is what elicits sycophancy.

Abstract: Large Language Models often generate factually correct responses that fail to maintain user-requested perspectives, blending multiple perspectives and forcing users to filter through unwanted information---a perspective control failure that factual accuracy metrics cannot detect. We introduce PerspectiveBench, a benchmark quantifying perspective alignment by constructing scenarios where multiple valid reasoning paths coexist, and propose the Perspective Alignment Score (PAS) to measure adherence to specified perspectives. Experiments reveal that state-of-the-art models successfully include target content but fail to exclude non-requested perspectives. Providing documents through RAG improves factual grounding but does not resolve perspective drift, as models prioritize comprehensive coverage over strict user constraints. Code and data are available at https://github.com/sunghoon014/PerspectiveBench.

Abstract: Most older adults who hear a warning about scams hear it from someone they know: a relative, a neighbour, or a friend who was targeted. Yet research on scam prevention almost always studies one person at a time. We ask whether scam awareness can spread through a community and protect it the way a vaccine does, since a warning protects whoever hears it and can be passed on. To find out, we built Scam Town, a simulated community in which a large language model plays each resident. Scam centres phone the residents, and after a call a resident can warn the people they know. Word of mouth helped, but it did not take off on its own: each warning led to fewer than one more, so a community cannot count on warnings "going viral". Across 80 simulated towns, everyday talk cut the number of people scammed by roughly a fifth. The largest gains came when an official warning, from a bank, a senior centre, or an agency, reached most of a town and residents then talked about it: in simulation (a combination we did not test live) the two together cut scams by about half. Protection was greatest when warnings reached the people scammers actually call, who here were older residents. Because our residents are language-model stand-ins rather than real people, we treat these findings as predictions to test with people, not as proof. They point to a simple recipe for scam education: give people a clear story they can retell, design campaigns to be passed along, and reach first those most likely to be called.

Abstract: LLM agents can ask clarifying questions to complete tasks, but answering each question demands users' time and effort. Existing evaluations typically measure this burden by counting questions, treating necessary and avoidable questions equally. We propose an evaluation protocol that distinguishes how often agents ask from how well they ask. An interruption budget limits the number of questions, while a user-attention cost charges extra for questions that are hard to read or not worth asking, as rated by a human-validated LLM judge. Beyond question counts, this cost captures perceived effort: on conversation pairs with the same number of questions, human annotators agreed with the cost on which conversation required more effort 75% of the time. Across eight LLMs and four customer-service domains, limiting agents to one to three questions reduces user-attention cost by 36-73% while keeping 86-94% of the task reward they earn with unlimited questions. At the same budget, reviewing each question against the memory of users' earlier answers cuts attention cost by another 13% with little reward loss and yields more valuable questions. Models also differ sharply in how well they ask: at the same user-attention cost, the most efficient models gain more than twice as much reward from their questions as the others. These results show that asking less and asking better are distinct goals, and that evaluations of proactive agents should measure both.

Abstract: We study how to improve decision policies from observational data to generate better actions when actions are complex, structured objects, such as text messages or images. This task is subject to two major challenges: (i) action-level overlap is often too weak for reliable off-policy evaluation and improvement, and (ii) generating new structured actions often requires expensive training or fine-tuning (e.g., of an LLM) and can be ill-defined due to information loss in action representations. To address both, we propose PolicyLift, a three-stage framework for generative policy improvement with structured actions from observational data. In Stage 1, PolicyLift learns a small set of discrete action codes that capture high-level strategies in the observed action space and are tailored to support policy improvement under limited overlap. In Stage 2, it learns a context-dependent policy over these action codes. At deployment time, Stage 3 "lifts" the learned code-level policy back to the original action space by generating actions from the historical behavior system in a code-conditioned way. We show theoretically that improving the policy over action codes guarantees improvement of the induced policy in the original action space. We demonstrate PolicyLift across experiments in synthetic and real-world text generation tasks with consistent policy improvements over the behavior policy.

Abstract: In recent years, with advances in multimodal interaction technologies and the growing demand for intelligent emotional support, Multimodal Emotional Support Conversation (MESC) has emerged as an important task. However, existing systems still suffer from shallow responses and inappropriate support strategies due to weak semantic feedback, cross-dimension reward compensation, and coarse reasoning supervision. To address these challenges, we propose FACES, a fine-grained gated semantic alignment framework for MESC. Specifically, FACES integrates multi-source rewards to construct multidimensional semantic and functional alignment signals, employs a non-compensatory gated fusion mechanism to reduce cross-dimension reward offset, and leverages structured Chain-of-Thought (CoT) anchors to perform token-level credit assignment. Under a controlled response-length protocol, FACES improves the average MLLM-based evaluation score from 3.61 to 4.04 and achieves an 80.22% pairwise win rate over SOTA. Human evaluation under the same protocol yields a 75.3% preference rate. Results on three external datasets further support transferability. The code and dataset are available at https://github.com/OCT-ARR/arr.

Abstract: User feedback enables LLMs to refine reusable personalized skills, but often mixes persistent preferences with request-specific corrections. Indiscriminately retaining both risks negative transfer, motivating selective retention at the level of individual requirements. We frame this challenge as selective transfer over atomic rules and propose SkillGrain, a framework for learning reusable personalized skills from user feedback. SkillGrain decomposes feedback into independently actionable rules, predicts their transferability, and retains only those suitable for future requests. To learn these decisions, we combine rubric-guided skill rewards with fine-grained credit assignment that separately evaluates rule content and retention decisions. We further jointly optimize skill induction and skill-conditioned generation through reinforcement learning, ensuring that learned skills support downstream personalization. We construct a benchmark spanning five personalized writing tasks to evaluate cross-request generalization. Experiments across three base models in both in-domain and out-of-domain settings show that SkillGrain achieves the best overall average performance among competing methods.

Abstract: System One models choose an agent's next action by scoring a supplied set of options in a single pass. This makes them fast and cheap, but when they choose wrongly there is nothing to inspect: did the model misread what the agent has seen, or read it correctly and still act wrongly? We answer behaviorally. On a frozen benchmark of agent decision states from simulated environments, customer-service policies, tool use, web navigation and coding, we pair every next-action question with factual probes about the same state, each answered independently. Across seventeen fast systems and a reasoning model, the answer is consistent: most wrong actions follow correct reading, and the more accurate a system, the more of its errors take this form. These errors are not noise; they gather on the same states across systems of every kind. Where the probed facts provably determine the action, models that read every fact still fail to combine them, and their own answers, composed by code, repair the failure. On real states, what is missing is often not a fact but the next sub-goal.

Abstract: LLM agents increasingly operate over multiple entities, where reliable response generation requires not only retrieving relevant evidence but also preserving its association with the correct entity. We identify Phantom Merge (PM), an entity-evidence binding failure in which an agent attributes unsupported claims to its committed entity, potentially even when the task is completed correctly. We formalize PM at the claim level and characterize its prevalence and error subtypes across four agent domains and four backbone families. To address this problem, we propose a two-stage framework for claim-level risk estimation and correction. First, Anchor-Grounded Risk (AGR) combines a representational readout of the agent's pre-emission hidden state with Jacobian-based functional information, providing complementary slot-level and anchor-value risk scores. Second, Fixed-Anchor Correction (FAC) audits flagged claims and selectively revises them using observed anchor evidence or removes them when no supported replacement is available. On the held-out Shopping detection cohort, AGR-slot achieves an AUROC of 96.2% and an average precision of 97.3%, outperforming the evaluated detection baselines. In the end-to-end Shopping mitigation evaluation, FAC reduces trajectory-level PM from 51.4% to 6.2%, with an output-to-original claim ratio of 80.7%. These results demonstrate the prevalence of entity-specific grounding failures and the effectiveness of combining internal risk estimation with evidence-constrained claim correction. Our code is publicly available at https://github.com/LabRAI/PhantomMerge.

Abstract: Task-oriented conversational agents remain fragile under realistic conditions, especially when users exhibit non-cooperative behavior. Existing function-calling benchmarks underrepresent adversarial conversation trajectories, thereby limiting the training resources available for developing robust agents. We present MADS (Multi-Agent Dialog Simulation), a synthetic data generation pipeline that produces structured, diverse dialogue trajectories. We inject adversarial conversation, producing validated conversation trajectories that capture realistic, unhappy paths. Using MADS, we construct MADS-Bench: a benchmark spanning six domains, 55 personas, and 1095 conversations, with approximately 66% of conversations containing failure-prone conversation scenarios. We evaluate the robustness of the trained models using a two-stage training approach that combines supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR).

Abstract: As agentic systems gain commercial popularity, user simulators increasingly serve as measurement instrument for their evaluation. However, the fidelity of simulated users in comparison to real human users is generally low, and typically assessed by costly, subjective LLM judges. In this pilot study, we ask whether fidelity can instead be measured deterministically by treating a user persona sociolinguistically: as a social type that emerges from observable linguistic style, rather than one predicted by labels or descriptions a model must extrapolate into behaviour. We author personas as concrete stylistic rates, which lets us transfer two established, model-free instruments -- authorship-verification stylometry and lexicon-based content analysis -- as fidelity diagnostics. We A/B-test the sociolinguistic schema against a flat descriptive baseline across five task-oriented customer-service agents. Results show that the sociolinguistic schema improves both stylistic adherence and stylometric distinguishability for most of the tested models, with a caveat that persona style fidelity does not necessarily equal persona "naturalness". We argue that a sociolinguistic approach to persona design is a promising path towards more diverse and representative user personas, and that these metrics are most valuable in an error-attribution analysis, localizing where fidelity breaks down. This is a first step towards interventions that move user simulations closer to faithful renderings of diverse and variable linguistic outputs.

Abstract: Enterprise conversation analytics asks many questions of millions of interactions. Each question can require reconstructing what people mean and identifying which information matters, repeating costly interpretive work across the same transcripts. We propose a simple principle: clarify the text, then focus the reader. Statement normalization transforms dialogue into short, speaker-attributed statements with source references and semantic tags. The statements make meaning more explicit; the tags support selecting evidence for a particular question. Downstream models can use the full representation or a relevant subset, depending on what helps them make the decision. In an offer-suppression task on customer-service calls, normalization improves a supervised classifier without selection, while weaker prompted readers benefit from both normalization and selection. A small model can learn the normalization contract, while lightweight encoders handle tagging and downstream decisions. Sharing this preparation across questions supports an inference pipeline built entirely from small models, making analytics over millions of conversations substantially less expensive.

Abstract: Memory can sustain AI companionship, yet even accurate recollection can be inappropriate to use. Two rounds of formative interviews with 14 users (n = 6 exploratory, n = 8 memory-focused) motivate asking what a companion should consider before using past information. Eight themes inform Reconsider, a single-call procedure with five checks and four handling modes, evaluated on 80 scenarios across five models over 400 blinded within-model pairs. Two LLM judges favored Reconsider by net margins of +15 and +23 percentage points, with bootstrap intervals excluding zero for three of five models but not for GPT or Claude. Evaluator analysis linked judge scoring differences to model family, and a preliminary matched-guidance control isolating memory-specific content gave positive margins. We contribute an interview-grounded design framework for memory use and an evaluation that scrutinizes its own evaluators.

Abstract: We present a hybrid quantum-classical framework that detects affinity and romance-investment fraud by modelling the cognitive biases in a manipulative conversation. In our proposed framework, cognitive biases central to this fraud class are carried by dedicated qubits in a structured parameterized quantum circuit, together with a frame qubit makes the encoding sensitive to the temporal order of manipulative reframing, and a narrative qubit that aggregates co-occurrence through a trainable entanglement layer. The circuit parameters are trained jointly with a classical reinforcement-learning agent that decides, turn by turn, whether to flag the conversation, modeled as an optimal stopping problem. We evaluate the model's performance on synthetic conversations that include hard negatives, legitimate but urgent, and legitimate but pushy sales conversations.

Abstract: Language models provide a plug-and-play interface between humans and robots, but important challenges remain when speech, dialogue, fast interaction, and collaboration are required. We propose a benchmark for the community to use as a way to explore common spoken dialogue artifacts between robots and humans, including requests for clarification, interruptions, embodied signals (e.g., head nods or facial cues), and time constraints. We also explain our vision to extend the benchmark for other aspects of human-robot interaction that are important to the larger research community. To facilitate the benchmark, we further propose using \textit{Retico}, a real-time communication framework that fulfills important technical requirements to enable robots to have spoken dialogue capabilities.

Abstract: LLM agents are starting to own the full customer experience. Soon, LLMs may be selling and buying on behalf of companies and customers respectively. Small models are more cost-efficient at scale, but can reinforcement learning train them into competent sellers? We train four Gemma 4 checkpoints (2.3B to 31B effective parameters) with GRPO on a programmatic utility reward for bilateral multi-issue bargaining, and evaluate every arm on the same 1,152 negotiations against two frontier buyers it never saw in training. With the same learning rate ($10^{-6}$) for every size, the gain of the RL model over its base rises from $+0.001$ at 2.3B to $+0.078$ at 31B. Each size was trained once and the two smallest checkpoints use a different architecture, so we fit no scaling law. Tripling the learning rate, with the same or fewer training steps, improves on the shared rate at every size by $+0.032$ (2.3B) to $+0.081$ (4.5B). In exploratory comparisons with two frontier models run as sellers, the 12B seller trained at the tripled rate scores above both, though its untrained base already scores as high as they do. The 4.5B seller at that rate shows no detectable difference from either and fits on one 48 GB GPU. A further 2.3B arm at ten times the shared rate raises pooled score, but its gain concentrates on the evaluation buyer that shares a model family with the training pool. These results suggest tuning the learning rate before concluding that a small model cannot learn to negotiate, and testing against buyers from more than one model family.

Abstract: Natural face-to-face human--robot interaction requires a robot to understand an evolving social situation, decide when to engage, and express its intent through coordinated physical behavior. Yet existing approaches rarely close this loop: foundation-model agents provide increasingly capable multimodal reasoning and memory but remain largely disembodied, while expressive virtual agents do not face the physical constraints of real robots, and physical social robots typically address social reasoning and embodied expression only partially. We present ARISE, a unified framework that bridges Agentic Reasoning and Interactive Social Embodiment on the Sophia humanoid robot. ARISE integrates multimodal context understanding, long-term memory, and reactive and proactive interaction to determine when and what to communicate, and translates social intent into robot-native gestures coordinated with speech and mechanical facial expressions through streaming execution. Extensive evaluations on Sophia demonstrate strong perceived interaction quality, expressive and well-coordinated embodied behavior, and substantial latency reductions through streaming execution. These results highlight the importance of jointly reasoning about what to communicate, when to engage, and how to physically express social intent for natural interaction with humanoid robots. Project Page: https://robosocial.github.io/

Abstract: Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent memories can also induce sycophancy, causing agents to over-align with users' historical beliefs even when they are inaccurate, outdated, or inconsistent with objective evidence. Existing mitigation methods assume that memory-induced sycophancy originates from biased or incorrect memories and attempt to reduce this risk by filtering such memories at different stages of the memory pipeline. However, in the real world, objective and correct memories can still induce sycophancy, and the same memory can warrant different influence across different contexts. To this end, we propose MemAdapter, a novel framework that adaptively integrates retrieved memories to support objective and reliable reasoning. Specifically, MemAdapter consists of three components: (i) Counterfactual Induction, which leverages counterfactual reasoning to uncover the potential risk of retrieved memories; (ii) Context-Aware Reflection, which calibrates the inferential influence of each retrieved memory in light of the current task via self-reflection; and (iii) Evidence-Based Reasoning, which grounds the final response in appropriate evidence while preserving the legitimate influence of memory. Extensive experiments on three benchmarks demonstrate that MemAdapter consistently improves memory reliability across diverse scenarios. Our code is available at https://github.com/DEEP-JLU/MemAdapter.

Abstract: Building LLMs that behave well socially, not merely correctly, requires Building LLMs that behave well socially, not merely correctly, requires more than producing locally helpful responses. A socially competent agent must infer users' unstated goals, respect their preferences, and adapt as the conversation unfolds. These behaviors are inherently multi-turn and social, making them hard to optimize: real interaction data is scarce, and user preferences are typically latent rather than directly observable. To address these challenges, we build on a persona-driven social simulation environment (consisting of a persona library, LLM-based user simulators, and a user-satisfaction scoring system ranging from [0, 1]), to introduce preference-batched GRPO (PB-GRPO), a post-training algorithm that learns socially adaptive policies from conversation-level feedback. Compared to vanilla GRPO, PB-GRPO computes advantages using a normalization estimated across a bucket of users with similar preferences, stabilizing training across a diverse social population. Empirical evidence shows that PB-GRPO improves models' social behavior over strong reinforcement learning baselines in our simulated environment.

Abstract: The evolution of linguistic style in conversations is an underexplored issue in NLP. Most style-control datasets focus on sentences or assume a static style throughout, missing the dynamic shifts that occur as user preferences change during interactions. We introduce ConvoDrift, a dataset designed to model progressive stylistic conversational tone drift under fixed semantic intent. It is built on 15,727 shared multi-turn conversational structures for adaptation and persona-conditioned alignment methods. It consists of six prompt-response pairs per conversation, each with the annotation of style drift and style direction labels. These pairs cover a range of communication genres. We further derive a complementary pairwise dataset by pairing semantically equivalent but stylistically distinct responses and annotating persona-conditioned preferences using five distinct style communication personas, enabling the controlled study of personalisation and pluralistic alignment in language tone. In addition to dataset construction, we conduct a comprehensive evaluation involving human validation, LLM-as-judge assessment, and automatic lexical and semantic evaluations. Across seven Likert criteria annotated by three human annotators, the average Krippendorff's alpha is 0.88, and our lexical and semantic analyses show that drift events induce lexical changes while preserving semantic similarity.

Abstract: A companion that talks with a person for months should come to understand them. It should remember what they said, infer who they are, and know when the past bears on the message in front of it. Testing this requires a real person's record, and such records are private, so benchmarks generate the person and the questions and settle in advance what matters. We release \bench, ten real relationships with an AI companion: 27,218 messages over up to 120 days, released as the conversation and four files derived from it, a profile, a persona, a chat ground truth and a question set, each citing the messages it rests on. Every chat label carries the reasoning trace that produced it, checked stage by stage against the conversation. Three findings follow. First, the past is rarely needed and far away. Pooled measures mislead: a recency window finds the required message for 95.9\% of probes and 2.2\% of those that need memory, and at the natural rate 96\% of the gain from supplying recorded evidence comes from messages that need none. Second, no detector we tried can tell when memory is needed on real messages, authored questions over the same histories leak the cue, and labeling the same messages as memories raises their use by ten to fourteen points. Third, three agent systems reconstruct the persona with the same F1 at a 31-fold difference in cost.

Abstract: Trustworthy Legal AI requires systems that can answer legal questions while grounding their responses in authoritative sources. However, existing Vietnamese legal benchmarks provide limited coverage of real-world legal consultations. We introduce \textbf{ViLegalExpert}, a large-scale benchmark constructed from authentic citizen--lawyer consultations, containing over \textbf{172K} questions across \textbf{34 legal domains}, together with professional answers and expert-verified legal evidence. ViLegalExpert supports legal information retrieval, extractive QA, and abstractive QA. Experiments with representative retrieval methods and language models reveal substantial challenges in evidence retrieval and grounded answer generation. While pretrained models perform strongly on QA, hybrid retrieval achieves the best retrieval performance. These results demonstrate the difficulty of mapping naturally expressed legal questions to authoritative provisions and establish ViLegalExpert as a challenging benchmark for reliable Vietnamese Legal AI.

Abstract: Emotion recognition in conversation has been widely studied, but applying Large Language Models (LLMs) to continuous dimensional emotion evaluation in multimodal dialogue remains largely unexplored. We propose an LLM-based framework that performs discrete emotion recognition and Valence-Arousal-Dominance (VAD) dimensional evaluation on IEMOCAP, incorporating acoustic cues as natural language descriptions following the SpeechCueLLM approach. We evaluate six models spanning the LLaMA, GPT, and Qwen families under zero-shot prompting, few-shot prompting, and LoRA fine-tuning. LoRA fine-tuned LLaMA models substantially outperform prompt-engineered GPT models on both tasks despite GPT's larger scale, a gap we attribute to domain adaptation rather than model capacity. Our best model achieves a Valence CCC of 0.7822, a new state-of-the-art on IEMOCAP. Ablation studies confirm that textual audio descriptions meaningfully improve smaller models (+3.5 to 3.6 weighted F1) while contributing little for the largest model, suggesting audio cues are most valuable when linguistic capacity is limited. The performance asymmetry across VAD dimensions closely mirrors the annotator agreement hierarchy in IEMOCAP's own annotations.

Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive agents mainly studies whether and when an agent should act on its own, not what information it should pursue. We study a distinct axis of proactivity: its content. Horizontal proactivity pursues unstated information that the current context already identifies, and vertical proactivity pursues needs that only earlier evidence reveals. A need graph, recovered from a benchmark's own decomposition, records which needs depend on which, so both forms, and whether the agent stops at the right time, can be scored from a transcript without a model judge. To learn this behavior, we propose Q&D (questioner and drafter), which trains a questioner to prefer the question whose continuation retrieves more of the required evidence, with no reward model or judge. On held-out splits of three multi-hop question-answering benchmarks, at equal retrieval spend, the trained questioner improves both forms of proactivity over the same model, prompted, and outperforms a prompted model $15\times$ larger in the same role on two of the three, and the gain persists after controlling for question volume and length. Without further training, we place the questioner in an interactive customer-service agent with a simulated customer, where it completes more tasks while asking fewer questions, and in retail it outperforms the $15\times$ larger model with fewer follow-up turns from the customer. These results show that proactivity depends not only on whether an agent acts without being asked, but also on what it chooses to pursue and when it stops.

Abstract: Proactive dialogue requires agents to continually adapt their policies to user feedback while progressing toward task objectives over multiple turns. To move beyond imitation learning on static datasets, recent approaches use user simulators to collect interactive data for policy optimization. However, many simulators do not explicitly model the evolution of user cognition, limiting the consistency and state dependence of feedback across turns. Moreover, representing each action only by a high-level strategy label overlooks the large utterance space and cannot distinguish alternative realizations of the same strategy. To this end, we jointly design a $\textbf{Cog}$nitive User $\textbf{Sim}$ulator $\textbf{(Cog-Sim)}$ and $\textbf{C}$ognitive-$\textbf{S}$tate $\textbf{T}$ransition--Driven $\textbf{P}$olicy $\textbf{O}$ptimization $\textbf{(CSTPO)}$. Cog-Sim maintains the user's cognitive and affective states and generates responses through constrained state transitions across turns, so feedback depends on both the realized utterance and the user's current state. CSTPO organizes each action as a hierarchical strategy--utterance representation: a high-level strategy label constrains utterance sampling, and utterances are optimized within each label. Sparse complete-branch sampling reuses shared dialogue prefixes and estimates separate strategy-level and utterance-level advantages, enabling fine-grained optimization at both levels. Across three tasks, Cog-Sim exhibits monotonic dose--response relationships and is preferred over prompt-based simulators for naturalness. CSTPO improves Qwen3-14B's performance to a level comparable to that of GPT-5.5-based planning methods.

Abstract: Large language model (LLM) agents serving different users often solve related tasks, yet separate user histories can leave reusable experience inaccessible to other agents. Pooling memories expands access but risks transferring preferences that conflict with the receiving user's requirements. We introduce ShareMem, a memory architecture that shares reusable experience while grounding its application in the receiving user's own preferences. Shared experiences indicate how to act and which preferences to consult; the receiving user's memory supplies their concrete values. Two-stage consolidation refines experience locally before integrating accepted edits into a shared pool. During execution, scope-first retrieval jointly selects local and shared experiences under a common entry budget, while a user-bound channel supports initial and agent-initiated preference retrieval. We evaluate ShareMem across web navigation (Mind2Web), online personalized interaction (VitaBench~2.0), and multi-session coding (MemoryCode) with four backbone models. It improves step success, average task success, and dialogue-macro coding scores, respectively, over matched user-local memory across all four models. Ablations favor two-stage consolidation for smaller shared pools, lower induction token usage, and better downstream performance, and support complementarity between experience guidance and active preference retrieval. Further analyses show that sharing helps most when relevant local experience is scarce, while source quality and cross-user preference interference limit useful transfer.

Abstract: Multimodal Sentiment Analysis (MSA) aims to infer human emotions from multiple modalities such as text, audio, and vision. In practice, inputs are often corrupted by noise and missing modalities, which degrades performance. Existing methods typically address these challenges in isolation, limiting their effectiveness in realistic settings. To address this limitation, we propose a Reliability-aware Cross-sample Enhancement (RCE) framework. Specifically, RCE first introduces an adaptive variational information bottleneck to model modality-wise uncertainty and perform quality-aware information compression, thereby suppressing redundant noise in unreliable modalities. Furthermore, we design a reliability-aware cross-sample enhancement strategy that retrieves high-confidence, semantically consistent neighbors from a large candidate pool to enrich and calibrate current representations, effectively alleviating information deficiency caused by missing modalities. Building upon this, RCE integrates cross-modal interactions with a multilevel reliability-aware fusion mechanism to adaptively aggregate information across modalities and enhancement stages, leading to more robust multimodal representations. Extensive experiments demonstrate that RCE consistently outperforms state-of-the-art methods across full, noisy, and missing-modality settings.

Abstract: Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational policies and use tools reliably. Manual end-to-end testing offers limited coverage, while live experiments expose customers to failures that can erode trust. We present a hypothesis-driven simulation workflow for screening candidate CX agents before deployment. Synthetic customers react to agent responses and simulated tool outputs enable multi-step agentic workflows without invoking production backends. We use the Snowglobe simulator on Nubank's Card Delivery agent and its expanded successor, Card Management - Nubank's highest-volume chat-support agent in Brazil. Across 4 deployed versions, simulated and production version-level binary evaluator scores show high correlation. Simulation-guided iteration increased transactional net promoter score (tNPS) by 36.69 points in a live A/B test. We also screened open-weight configurations in over 16,000 simulated conversations. In a subsequent live A/B test, the selected model increased self-service rate (SSR) by 8.82 percentage points to the highest level observed at Nubank, with no statistically significant change in tNPS. Simulation made broad exploration of models, reasoning settings, and prompts feasible without customer exposure, enabling production improvements that would have been impractical to pursue through live experimentation alone.

Abstract: Measuring how successful a conversation is remains difficult, even for humans judging spoken dialogue. We evaluate state-of-the-art LLMs as pointwise and pairwise judges of conversational success on CANDOR, finding pointwise scoring correlates moderately with human ratings, while pairwise comparison suffers from long transcripts and positional bias. Since this leaves judge scores incomparable across models, we propose a small anchor set and a calibration function that calibrates any judge onto a shared, interpretable scale. We further release the Voice Arena Goal Dataset (VA), 200 task-oriented human-AI and human-agent conversations with pairwise annotations, revealing a substantial gap between current judges and human-level discrimination. Using VA, we test whether CANDOR-fitted calibration transfers to human-AI conversations, finding it brings judges onto a shared scale despite never observing VA during fitting.

Abstract: Audio-language models (ALMs) can exploit textual shortcuts to answer questions while overlooking acoustic evidence, weakening audio understanding. On-policy distillation (OPD) trains compact ALMs by supervising student-generated responses with teacher predictions, but does not explicitly distinguish acoustic support from linguistic predictability. We propose Reward-Tilted On-Policy Distillation (RT-OPD) to strengthen acoustic grounding. Given the same question and student-generated text, a frozen teacher predicts the next token with and without audio inputs. Their log-probability contrast defines a reward that reshapes the teacher distribution for reverse-KL distillation, emphasizing the additional evidence provided by audio. Across two compact students and three benchmarks, RT-OPD consistently outperforms Vanilla OPD. Experiments with silenced and replacement audio further suggest that RT-OPD strengthens the student's reliance on acoustic evidence. Our 3B model achieves 72.72% accuracy on MMAU, the highest among the compared 3B models and competitive with several 7B and 8B models. Code and model checkpoints are available at https://github.com/KaiyangLi1992/RT-OPD.

Abstract: Faithful user simulation is fundamental to building, evaluating, and improving interactive AI at scale. However, plausible individual responses do not ensure that simulated users reproduce the intent evolution and outcomes observed in real interactions. We propose TRACER, a multi-turn user simulator that explicitly models users' evolving intent and learns to align simulated behavior with real interaction trajectories. TRACER is trained in two stages: supervised fine-tuning on real user dialogues, followed by multi-turn reinforcement learning. The RL stage combines hierarchical outcome- and trajectory-level rewards with deviation-aware advantage modulation, jointly mitigating reward sparsity and credit assignment in long dialogues. On real customer-service sessions organized into reference cohorts, TRACER-7B surpasses the strongest baseline by 11.4 conversion F1, while also achieving the lowest group-level conversion-rate error and semantic trajectory distance, and generalizing to out-of-distribution scenarios. Human Turing tests yield identification accuracy close to chance, supporting the perceived naturalness of generated conversations. Building on this simulator, we further introduce the Dynamic Marketing Benchmark, which jointly evaluates persuasion effectiveness and response quality of LLMs through simulated interactions, revealing that higher response quality does not necessarily correspond to higher conversion rates.

Abstract: Planning is a common yet complex activity shaped by constraints to satisfy and preferences to balance. Travel planning, as both an everyday activity and a frequent benchmark for evaluating intelligent systems, offers a rich context for examining how constraints and preferences emerge and evolve. While recent AI systems have achieved impressive results in generating personalized itineraries, they often assume that users can articulate stable goals upfront. To understand how real-world planning unfolds, we conducted a two-part interview study: one with eight travelers reflecting on their planning experiences, and one with nine travel agents sharing professional practices. We trace the dynamics of constraints and preferences as they are surfaced, refined, and coordinated throughout the planning process, and identified 11 actions revolving around constraints and preferences, which shaped the planning process. We offer design heuristics for planning tools that better support human-AI collaborative actions to support the fluid, contingent nature of planning.

Abstract: A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In parallel, work on social sycophancy has focused on behaviors such as validation and positivity that may signal inappropriate deference. Yet the markers of social sycophancy are also characteristic of conversational receptiveness, a construct from social psychology shown to improve interactions across disagreement. We argue that this overlap creates a construct-validity problem for social sycophancy evaluations. Using a popular moral-advice dataset, we find that responses classified as more socially sycophantic are also more receptive. Further, increasing the receptiveness of human-written responses---while preserving their substantive conclusions---causes them to be classified as more socially sycophantic. This tight coupling raises the possibility that social sycophancy evaluations inadvertently penalize desirable behavior. In a preregistered experiment comparing substantively equivalent responses, participants prefer the more receptive responses, expect users to be more likely to listen to them, and are more willing to seek advice from their authors. The same overall pattern persists even among participants who believe the original question asker is in the wrong. Finally, we introduce a simple approach that substantially increases receptiveness without increasing substantive deference, demonstrating that conversational receptiveness and substantive independence can be achieved together.

Abstract: Humanoid robots are increasingly being popular and developed for human-centered applications, yet their ability to provide intelligent conversations and natural interactive knowledge assistance remains constrained by traditional rule-based dialogue systems, pre-defined responses and limited knowledge repositories. Large language models (LLMs) have emerged as a powerful foundation for enabling natural, adaptive, and context-aware Human-Robot Interaction (HRI), which provides a significant opportunity to address such limitations by enabling robots to understand natural speech language, reason over complicated queries, maintain high-quality conversational context, and generate knowledge-rich responses. In this work, we originally present and implement an LLM-based versatile Conversational AI Knowledge Assistant for the Raspberry-Pi-powered 13-Axis MyBuddy humanoid robot, which integrates LLM-driven language understanding and AI reasoning with real-time speech recognition, knowledge retrieval via extensible access of internet engines (e.g., Wikipedia, arXiv), flexible dialogue management, and natural speech synthesis to enable much more intelligent multi-turn continuous conversations and advanced emotional-support Human-Robot Interaction.

Abstract: Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive generation on the critical path of memory operations. We introduce \textbf{\method}, a new agentic memory architecture inspired by System-One/System-Two cognition. System One captures fast, lightweight decision-making, whereas System Two performs slower, deliberative reasoning. Jev-Mem brings this division of labor to agentic memory through a dedicated System-One control plane, a structured multi-relational memory plane, and a System-Two reasoning plane. The System-One controller governs memory typing and relational organization during construction, and dynamically performs query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping during retrieval. System Two is invoked only for complex reasoning and answer synthesis. This design improves both memory effectiveness and system efficiency: on LoCoMo Jev-Mem achieves an overall LLM-as-a-Judge score of 0.777, an 11.0\% relative improvement over the strongest baseline, while reducing memory construction time to 158\,s, a 6.6$\times$ speedup over the fastest competing memory system, and lowering average query latency to 0.93\,s, a 36.7\% reduction.

Abstract: Interpreter agents built on machine translation (MT) increasingly mediate live conversation between people who do not share a language, yet we still evaluate them with metrics built for isolated sentences, which measure fidelity rather than whether communication succeeds. We introduce a reusable three-layer checklist-and-judge framework that evaluates interpreter-mediated conversation across semantic, pragmatic, and cultural-social dimensions, covering the naturalness, intent, and social appropriateness that fidelity metrics leave unmeasured. It runs in both single-turn and interactive multi-turn settings, where simulated users reply to translated messages as the conversation unfolds and each turn is scored alongside the conversation as a whole. We extensively validate it through controlled perturbations, cross-judge comparisons, and human annotations. Our main single-turn benchmark evaluates 10 interpreter setups across Arabic, Bengali, Indonesian, and Korean from 5,624 OpenSubtitles-derived scenarios spanning 12 translation directions, and our multi-turn study covers all 6 language pairs in scripted and live modes. Results show a consistent decline from semantic to pragmatic and cultural-social success, while conventional MT metrics overlook failures among stronger interpreters, and prompt ablations show that scenario context, structured instructions, and cultural context improve communicative success, although gains vary across setups. Our work thus provides an evaluation framework and benchmark for interpreter agents in conversation, and highlights the importance of communicative success alongside existing translation metrics.

Abstract: AI agents are usually evaluated by whether they complete a task. In interactive service settings, a successful agent can still frustrate users by asking repeated questions, performing redundant searches, or making avoidable revisions. We introduce RideWay, an efficiency-centered benchmark for ridehailing agents in a stateful tool-calling environment, together with Efficiency Utility, a success-gated metric that discounts successful trajectories for excess tool calls and user-facing turns relative to task-specific reference effort. Human paired preferences calibrate the relative penalties, reflecting an aggregate service-workflow trade-off: extra dialogue often creates visible friction, whereas extra tool use can sometimes verify constraints or preserve user intent. Across 58 tasks and 24 models, the fitted penalty for excess turns is about twice that for excess tool calls. On task-disjoint held-out preferences, Efficiency Utility achieves 78.7% accuracy overall: 90.6% when trajectories differ in turns, but chance-level accuracy when they differ solely in tool calls - the axis on which human annotators agree least. RideWay therefore makes interaction efficiency measurable alongside task success, while exposing the boundary of count-based tool-use evaluation.

Abstract: Large language models can produce fluent answers when their factual support is weak. This paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-only framework that makes answer commitment conditional on an explicit assessment of the information required to answer a question. We evaluate three CoSQ variants under seventeen conditions on the 817-item TruthfulQA multiple-choice validation set using eleven open-weight and hosted model families. In the final balanced-option protocol, Grounded-CoSQ at τ=0.90 reduces the mean unconditional wrong-commitment rate from 13.1% under chain-of-thought prompting to 8.9%, a 32.1% relative reduction, while increasing answered accuracy from 86.9% to 89.7% and answering 87.6% of questions. Both improvements hold for all eleven models and at every evaluated threshold. Critical-CoSQ and Adaptive-CoSQ provide neighboring operating points with 88.6% and 86.5% coverage, respectively, while remaining more reliable than the baseline. A secondary Natural Questions Short-Answer evaluation provides convergent open-form evidence. These findings show that self-assessment can support explicit, tunable answer-or-abstain decisions when an unsupported commitment is more costly than referral or review.

Abstract: As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the people they serve. Yet training such human-aware language models faces a fundamental supervision gap because current datasets for LLM assistant training contain few if any well-informed responses explicitly grounded in users' unspoken beliefs and goals. Scaling such supervision is inherently constrained, as users' underlying states are not directly observable. We thus propose the Mind2Dialogue framework to mitigate this gap by simulating users' mental states and turning them into privileged supervision for human-aware training. Specifically, we first propose a psychology-guided simulator that preserves personal characteristics while updating mental states through interaction to generate coherent conversations. The key idea is to enforce a shared evolving mental state that drives user behavior and guides an Oracle assistant's responses. Our privileged distillation then trains models on the Oracle's well-informed responses to assist users without direct access to their mental states at deployment. Moreover, we propose to evaluate human-aware learning by combining personalization and theory of mind, examining how models understand people and act on that understanding. Training on the full Mind2Dialogue corpus improves every reported personalization metric over the corresponding Qwen, Llama, and OLMo instruction-tuned baselines, including gains of 26.6 to 40.9 percentage points in preference-following generation. The gains extend to belief and action reasoning on Qwen and Llama, beyond personalized assistance. Looking forward, Mind2Dialogue makes user simulation a foundation for genuine AI collaborators that understand beliefs and intentions behind people's words and support their long-term goals across education, work, and everyday life.

Abstract: Visual feedback in the form of user-uploaded images and videos is becoming increasingly common in e-commerce platforms because it provides authentic evidence of product quality, defects, packaging conditions, and real-world usage. However, visual feedback alone often lacks the contextual explanations and subjective opinions necessary for informed decision-making, while many users provide limited textual feedback due to the effort required to compose detailed reviews. To bridge this gap, we introduce image-grounded review assistance, a novel task that aims to generate editable review drafts from user-uploaded product images. Unlike conventional image captioning, which focuses on objective visual description, the proposed task requires product-specific understanding, sentiment estimation, and evidence-driven review composition under challenging real-world conditions, including degraded image quality, excessive zoom-in, target ambiguity, and partial product visibility. We propose a multi-agent vision-language framework consisting of four specialised roles: product grounding, visual sentiment estimation, visual evidence generation, and review synthesis. The framework employs explicit intermediate representations, including product entities, predicted ratings, and evidence summaries, to improve interpretability and visual grounding. Experiments on a curated subset of the Amazon Reviews Electronics dataset demonstrate the feasibility of generating coherent, product-aware, and sentiment-aware review drafts from visual feedback. To the best of our knowledge, this is the first study to formulate image-grounded review assistance as a multi-agent vision-language reasoning problem, providing a practical step toward AI-assisted review authoring in e-commerce systems.

Abstract: Persistent agents need evaluations that distinguish identity facts they can recall from those they express and enact. We introduce PAI-Bench, a provider-neutral benchmark for fidelity to a versioned, update-governed identity contract. It separates recall, composition, behavioral enactment, resistance, persistence, lineage, and role-conditioned updates while keeping scoring oracles outside the target process. Two frozen campaigns cover sixteen synthetic profiles, thirty-two probes, and three independently initialized target configurations, yielding 1,536 retained responses. A judge-independent literal audit finds direct-parent identifiers in 48/48 atomic responses but only 1/48 implicit self-portraits. On eight profiles, explicit field cues increase joint presence of three identity identifiers from 0/8 to 7/8 under the same four-sentence instruction. A separate startup body-label substitution increases full-designation presence from 1/8 to 7/8 while parents remain absent. These contrasts reveal prompt-dependent component selection and component-specific sensitivity to startup cues in the tested deployments. Replaying identical factorial responses also yields a Claude headline mean 12.5 percentage points below Astra's, demonstrating evaluator sensitivity separately from target behavior. The studies use single target samples per condition, with post-hoc audits and follow-ups. PAI-Bench provides a reproducible evaluation protocol for measuring factual availability, identity expression, and behavioral enactment as distinct aspects of identity-contract fidelity.

Abstract: Recent multimodal sentiment analysis studies increasingly adopt text-centric fusion approaches to exploit the rich sentiment information inherent in the textual modality. However, these approaches often suffer from performance degradation during inference due to partially missing or noisy data in real-world scenarios, especially when sentiment-related cues are missing. To address this issue, we introduce a new completeness estimation approach that quantifies the degree of sentiment-relevant information preserved in incomplete data to guide the reconstruction of missing semantics. Furthermore, we propose a training strategy that stabilizes multi-task learning while jointly optimizing sentiment prediction and completeness estimation. Extensive experiments and in-depth analyses on three benchmark datasets demonstrate that the proposed approach enables more accurate semantic reconstruction, leading to more precise sentiment prediction.

Abstract: Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collaborators, it is central to building effective and trustworthy human-AI interaction. Existing reinforcement learning methods optimize single-turn utterances and sparse outcome rewards, producing short-sighted policies that struggle to manage goal-relationship tensions across multi-turn interactions. We propose SocialRL, a multi-turn reinforcement learning framework addressing both challenges. First, we apply multi-turn reinforcement learning using PPO that propagates delayed outcome rewards back to each turn, enabling long-horizon planning. Second, we design six process reward dimensions capturing the goal-relationship trade-off, including goal advancement, relational attunement, contextual coherence, etc. A reward model dynamically generates fine-grained scoring criteria for each dimension, while a stage-aware weight schedule prioritizes relationship-building in early turns, goal advancement mid-way, and balanced closure late. Across multiple social-dialogue benchmarks, SocialRL improves Goal Achievement by an average of 9.2 percentage points over the corresponding Base models. These results demonstrate the effectiveness of SocialRL across synthetic and real social scenes, as well as standard and challenging social scenarios.

Abstract: Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interpersonal relations in multi-party scenarios underexplored. In this work, we introduce relation-aware emotional support conversation, a new task that evaluates whether LLMs can capture and utilize the evolving dynamics of relationships to offer more effective emotional support. We construct RESCUE (Relation-aware Emotional Support Conversation Understanding and Evaluation Benchmark) from real couple and family interview conversations, containing 191 samples, 7,079 annotated turns, and 1,064.8 minutes of video. Based on rich annotations of socio-emotional and support-related dynamics, RESCUE defines six tasks that evaluate two core capabilities required for relation-aware emotional support: Relational Understanding and Relation-Sensitive Support. Experiments with ten LLMs show that current models perform relatively well on tasks relying on local emotional or intervention cues, but struggle with relation-intensive tasks such as relation pattern prediction, viewpoint prediction, and support strategy prediction. These findings reveal the limitations of current LLMs in modeling interpersonal relations and making relation-sensitive support decisions.