technical writers

Abstract: Deep research agents are increasingly capable of searching the open web and synthesizing evidence, yet they remain poorly suited to controllable report generation in multimodal deep research. This task requires agents to handle interleaved textual and visual inputs, gather multimodal evidence through multi-step web search, and deliver comprehensive illustrated reports under user-specified requirements. Existing systems face two limitations. During reasoning, they often underuse images discovered along the search trajectory; during generation, they tend to produce fixed-form answers with limited control over report granularity, multimodal composition, and evidence grounding. We introduce MIRA, a Multimodal Illustrated Deep Research Agent for controllable reports. MIRA integrates textual and visual evidence throughout research and writing. At its core, MIRA-Harness translates user requirements into generation contracts and connects four stages: evidence collection, report submission, feedback-driven revision, and final delivery. Building on this harness, MIRA-Data constructs high-quality multi-hop multimodal research trajectories, and we post-train foundation models to operate within the workflow. Using Qwen3.6-35B-A3B, MIRA achieves state-of-the-art performance among open agents on 7 representative, established multimodal-search and deep-research-agent benchmarks, while producing user-aligned illustrated reports with traceable textual and visual evidence.

Abstract: Few-shot prompting is useful when instructions and rewards are hard to specify. One such application is editing by example, where a demonstrated formatting change or API migration may need to be applied across multiple sites. However, such edits often depend on both left and right context, making generation with causal autoregressive models awkward. We therefore introduce multi-target few-shot prompting with diffusion language models, where examples guide the infilling of multiple masked regions within a shared canvas. To address the known challenge of reliably following demonstrations in few-shot prompting, we further leverage selective masking of the canvas to derive a likelihood-ratio reward that favors example-supported infills. Across few-shot prompting benchmarks and software refactoring case studies, we find that demonstrations improve infilling accuracy, with example guidance yielding further gains in several settings.

Abstract: Language plays a crucial role in research and technology design, throughout problem formulation, method descriptions, analysis of findings, and interpretation. In this paper, we focus on a particular, trending linguistic pattern in the Human-Computer Interaction literature, which we call -abilities. Examples include usability, accessibility, and explainability. These -abilities have become increasingly popular, with potential impacts on the discipline. They take a verb, turn it into an adjective, and finally nominalize it. We approach the -abilities phenomenon with a survey of the HCI literature between 1988 and 2025. All in all, we identified 349 different -abilities. Moreover, the use of -abilities notably increased since the late 2000s, both in the absolute number of different -abilities and the frequency of use of the most popular ones. The majority of -abilities we found had a positive notion, and most -abilities with a negative notion are prefixed counterparts of their positive opposite (e.g., un+sustainability). We critically discuss implications of their increased use. First, -abilities change the literal meaning of design intentions. For example, acceptability reduces the concrete verb accepting into only its potential (acceptable), and finally nominalizes it, claiming the existence of acceptability as a somewhat stable and real, abstract characteristic of a technology. Second, the prefix-based opposite construction can weaken the design goal. Un+sustainability avoids clarification of the -ability's meaning (here e.g., ecological or financial), and does not spell out the expected impact of designs that are not sustainable (e.g., the destruction of nature). Future work should compare the use of -abilities in English with other languages to better understand the ways in which they transform meaning.

Abstract: Large language models (LLMs) demonstrate strong individual task performance, yet still struggle to collaborate with users over extended, multi-turn interactions, for example by attempting solutions before understanding the user's needs or by failing to revise mistaken assumptions after receiving feedback. We propose Collaborative Theory of Mind (CToM), a framework that addresses these challenges by explicitly training LLMs to anticipate user responses and to use those predictions to improve their own behavior. CToM drafts a response, predicts how the user will respond, and uses this prediction to guide internal revision before presenting a response. During training, the user's reply to each draft serves as the target for predicting the next turn, and we train the assistant to minimize the negative log-likelihood of that reply. We combine this prediction objective with group-relative policy optimization (GRPO) to optimize both task performance and interaction efficiency. Across mathematical reasoning, coding, and writing tasks, CToM achieves higher collaborative task performance than all baselines; for example, on a collaborative mathematical reasoning task, it improves final accuracy from 74.1% to 79.6% compared with naive GRPO. Ablations show that predicting user responses also makes collaboration more efficient: under the same reward, adding prediction supervision reduces the number of user replies by 8% on coding and 17% on writing while improving task performance. Behavioral analyses of interaction trajectories show that user-response predictions become more accurate after training, and that more accurate predictions are associated with larger improvements in collaborative task performance through self-revision.

Abstract: As AI agents work alongside humans in shared workspaces, a mutual awareness challenge arises: agents act at speeds that outpace human monitoring, and users' evolving interests are not always expressed in chat. This challenge is especially pressing in literature review, where both parties retrieve, read, and synthesize a growing body of papers. We present Ream, a literature review workspace that supports mutual awareness through structured artifacts, bidirectional engagement tracking, and localized visualizations. Users can see each party's activity within these documents, and agents can retrieve the same history to guide their work. In studies with eighteen researchers, participants used these traces to inspect evidence, steer agents, communicate through annotations, and reflect on their research focus. Shared histories also helped agents build on earlier work. These findings inform how engagement traces within shared documents can support transparency, personalized assistance, and coordination in human-agent knowledge work.

Abstract: Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to perform this form of literature-grounded ideation remains challenging, as existing approaches based on prompting or feedback lack structured supervision for how papers should be synthesized. We introduce IdeaAnchor, a paradigm for training LLMs to perform research ideation using structured specifications as privileged signals. Each IdeaAnchor instance encodes how each input paper should be synthesized into a successful idea, including their functional roles, relationships, and target synthesis criteria. We build this paradigm by mining instances from published papers, capturing how real ideas emerge from prior literature. We then train models via demonstration, self-distillation, and reinforcement learning, and further enhance generation with retrieval at inference time. Experiments show consistent improvements in ideation quality. Our analysis reveals a functional decomposition: anchor-based training strengthens creative synthesis, retrieval enhances detail elaboration, and combining both yields the best performance.

Abstract: Scientific language models often access literature through untyped text chunks, which fragment the functional and evidential structure required for mechanism-rich questions. We introduce an evidence-grounded mechanism knowledge substrate that organizes scientific literature into provenance-linked evidence units, role-typed entities, and directed mechanism paths. We instantiate it as MS$^3$, a Material-Sensor-Signal-System schema for conductive-fiber flexible sensors, over 13,689 papers, 131,083 evidence items, and 26,648 mechanism objects. On in-domain and coverage-shift question-answering benchmarks, we compare closed-book generation, Web search, Raw-PDF RAG, and MS$^3$ retrieval across ten language models. MS$^3$ improves macro-averaged scientific correctness. It also improves citation entailment and answer completeness. These results support mechanism substrates as a reliable representation layer for scientific language models and motivate a source-repair workflow in which insufficient MS$^3$ evidence triggers targeted retrieval from its linked papers rather than assuming that a user has already supplied the correct PDFs.

Abstract: Collaboration depends on shared context, and technical documentation is one way that context persists across people and AI teammates. Specificity, the amount and exactness of detail expressed in language, shapes what information documentation captures and how precisely that information is communicated. This work audits sentence-specificity scoring artifacts on technical documentation and tests whether scores applied only after generation help choose among fixed LLM-generated revisions. Across Wikipedia and three technical-documentation corpora, the fixed general-domain predictor SpeciTeller and the pinned post-publication author-repository implementation of Ko et al.'s target-adapted predictor produce different corpus orders and same-sentence rank agreement from -0.066 to 0.510. Strict filtering and token-length adjustment change these patterns without reconciling them. In the Gemma set, SpeciTeller ranking raises direction-valid selection from 71.7% to 83.3% (+11.7 points; 95% source-case bootstrap interval +1.7 to +21.7); in the GPT-OSS-120B set, SpeciTeller ranking raises direction-valid selection from 51.7% to 56.7% (+5.0 points; 95% source-case bootstrap interval -6.7 to +16.7), and every primary single-score GPT-OSS-120B interval includes zero. These findings tie score interpretation and decision value to the predictor and candidate set.

Abstract: Writing with AI agents turns a paragraph into the outcome of many requests, yet the finished document rarely explains which request produced which change. We introduce Reactant, an interaction paradigm in which authors place typed inline annotations in their original documents. A verified transaction protocol records each request, skill identity, and the correspondences that identify additions, deletions, and transformations. The kernel validates the witness against the recorded states to establish word-level longitudinal lineage. We demonstrate Reactant through this paper's revision history, and report four months of three colleagues' self-directed use. Their uses include conversational inquiry into history and deriving reusable skills from recurring requests, illustrating how the transaction record serves as an extensible substrate for agentic authoring.

Abstract: We introduce DoGBENCH (Documentation Generation Benchmark), to our knowledge, the first benchmark for generating and maintaining real user-facing software documentation. It asks whether an agent can produce documentation that experienced technical writers would accept in review. The benchmark contains 292 items from open source projects, including Helm, PostHog, and Mautic. Each item gives the agent a pre-change repository and a trigger, such as a code pull request or a reported documentation gap. The agent must first decide whether the documentation needs an update. For items that need one, the agent must produce an acceptable patch in one attempt. For items that do not need updates, the agent must abstain. Task-specific rubrics, validated with project maintainers, score each patch on accuracy, completeness, reader guidance, placement, and repository conventions. The composite score combines patch quality with correct abstention, and a score of 100 means an agent meets every requirement for the task. Scores should not be interpreted as a percentage of an expert's capability. We evaluated seven agents. The highest-scoring agent reached 47.3 out of 100 on the 117-item held-out split. In a separate audit of 1,267 patches, the most common failure modes were task-completion gaps (45.5%), technical inaccuracies (36.6%), and incomplete conceptual or reference coverage (32.5%). Analysis of the corresponding trajectories identified three key patterns associated with these failures: (1) describing interfaces without examining how readers use them (36.0%), (2) missing decisive evidence and filling the gaps with plausible assumptions (33.1%), and (3) stopping after finding the first plausible documentation surface and leaving other affected pages stale (30.1%).

Abstract: Scientific method diagrams express computations through entities, dependencies, and conditional routes. Although generated figures can be improved through repeated editing, it is less clear whether experience from one paper improves the first figure of another. We present \sys, a framework for source-grounded adaptation of reusable diagramming skills, and study transfer through a complete-candidate evaluation. The framework links critiques to source passages, proposes bounded edits to a persistent skill library, and separates candidate competition from skill acceptance. We evaluate the original skill and four learned candidates on two NLP and language-agent papers, with two fresh generations per condition. The strongest candidate attains 87.50\% required-relation accuracy compared with 83.33\% for the original, while candidate behavior differs across papers. Local improvements on a separate development paper and automatic selector preferences do not establish consistent transfer. Tracing all 22 non-correct relation judgments to their production prompts reveals both incomplete conditional specifications and ambiguities despite explicit instructions. All ten planning diagrams leave an already-terminal selected leaf's route unclear; none of their prompts explicitly binds that route. Our findings show why evaluating reusable diagram skills requires source-grounded relation assessment, complete candidate coverage, and inspection of both prompts and images. We provide all twenty transfer outputs, skill snapshots, assessment records, and executable analyses.

Abstract: We present ChunkRank, an open-source Python library that derives chunk boundaries from a target model's tokenizer and context window, and selects an answer among candidates produced independently per chunk. It ships a validated registry of 90 models across 15 providers and six answer-selection methods, and needs only three core dependencies. For chunking, ChunkRank avoids context-window overflow automatically from the model name, whereas character-based splitters overflow or waste the budget, and a fidelity study across 11 languages shows why token-exact budgets matter beyond English. For answer selection we report a negative result: on NaturalQuestions, TriviaQA and HotpotQA, with extractive and generative readers, no content-based ranker reliably beats taking the first non-empty answer. The reason is reader abstention on chunks that lack the answer, not answer position. A long-context baseline shows that chunking matches single-call reading on single-hop questions, so ChunkRank targets small-window and beyond-window settings. Code, registry and evaluation harness are released.

Abstract: Eye-catching graphics, such as circular figure labels and word-scale visualizations, are increasingly being placed directly within long-form text paragraphs. Some research has claimed that inline visualizations can help readers understand data-rich passages more clearly. However, research in the science of reading calls into question the introduction of images within the flow of text. In this work, we conduct an exploratory study of eye movement in both the presence and absence of visual embellishments. Using a high-resolution eye-tracker (EyeLink Portable Duo), we observed small mean increases in vertical and cross-column saccade rates among six participants, with substantial variation among readers and no detected difference in comprehension accuracy. Mean subjective ratings for the data-light circular-glyph passage indicated it is more distracting than its unembellished comparison passage. These exploratory observations differ from prior findings and motivate a larger, fully crossed study of inline graphics.

Abstract: In this work, we explore whether LLMs can accurately predict and explain plausible materials for vehicle components such as brake discs or fuel injectors without requiring extensive fine-tuning. We test and evaluate three approaches: a standard generative LLM baseline, a single-pass Retrieval-Augmented Generation (RAG) approach, and an iterative Chain-of-Verification (CoVe) variant. For retrieval, we rely on publicly available data using a domain-filtered Wikipedia corpus. Since no gold standard exists for this task, we develop a custom web-based annotation tool supporting crucial functions for structured domain expert evaluation. LLM-based generation substantially outperforms prior work, which is not further surpassed by the tested RAG approaches. Our results surface remaining challenges for RAG-based systems: hyperparameter optimization, the availability of high-quality, legally accessible domain corpora, and expert evaluation study design.

Abstract: Specifications face a basic tradeoff: leave details out, and important questions go unanswered; record every detail separately, and the specification becomes large and prolix. We investigate whether a language model can serve as a compact, living specification oracle by learning facts about a target and answering questions about it directly. We compare two ways of storing the learned facts: external text notes and changes to the model's weights. Across four families of 596-fact worlds and two Qwen2.5 model sizes, weight-only oracles benefited substantially more from structure: with the 7B model, their accuracy integrated across storage capacities was 18.5 percentage points higher on structured than unstructured worlds, compared with 1.1 points for note-sheet oracles. This advantage came at a substantial storage cost, with the smallest adapter requiring approximately 175 KiB compared with a maximum note budget of 16 KiB. Adapted weights therefore exploited latent structure more successfully, while external notes required substantially less object-specific storage.

Abstract: A language model can resolve a writer's current organizing problem while the construction needed for her own resolution remains unfinished. I call this early epistemic settlement. The supplied organization meets every demand then governing the passage, yet proceeding from it can displace work through which the writer would have changed those demands or become able to form further organizations. I distinguish the coordination needed to complete an already formable organization from construction that changes which organizations are formable in the first place. Settlement in the first case changes the relative work still required to bring available organizations to sufficiency. In the second, it can remove the need for the work through which another organization would become formable. Even when supplied resolution and continued construction leave the same visible qualification, different dependencies in the writer's inquiry may support different later organizations. Model suggestions can also contribute to this development when writers work through them while the problem remains unresolved. In theoretical and exploratory writing, the relations developed in reaching local adequacy help determine what the writer can later defend or develop. A sound judgment that the present passage is sufficient can therefore make further inquiry dispensable before that generative work has occurred.