legal professionals

Abstract: Large language models (LLMs) are increasingly integrated into workflows that require reasoning over text documents, yet interaction remains largely conversational. This leaves argumentative structure implicit or embedded in text, making it difficult to maintain, compare, and revise arguments as analyses evolve. We present GroundWork, a mixed-initiative system that makes argument structure a shared, editable state for humans and LLMs. GroundWork operationalizes the Toulmin model of argumentation as a typed graph with explicit operations for human and LLM edits. It exposes this structure through coordinated corpus views and an editable workbench for constructing, comparing, testing, and tracing source-grounded arguments. We evaluate GroundWork through an expert study with four participants spanning consulting, product development, law, and immunology, and three use-case scenarios in intelligence, law, and medicine. Our findings show that GroundWork makes source-grounded arguments inspectable, comparable, and revisable as shared human-LLM state.

Abstract: Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems constructed from real-world legal, finance, medical, and software engineering corpora. TeamGym introduces a method to identify a minimal set of facts, each element of which is necessary and all of which are collectively sufficient for a correct final decision, which we call pivotal information. This enables TeamGym to both control the distribution of pivotal information and track how well agents identify and integrate pivotal information when making team decisions. Examining 8 language models on 12 source corpora, we find that current AI agents often fail to effectively share information: Distributing pivotal information across participants lowers success rate by 22.9 percentage points on average relative to giving the same information to a single model (a communication gap). We also document that participants do not effectively retrieve decision-relevant information on their own: A team's success rate is lowered by a further 19.9 points when participants must identify and extract pivotal information from source material rather than receiving it directly (a retrieval gap). To help remedy these deficits, we use TeamGym to train policies through reinforcement learning on team decision loss. Across two policy-training experiments, we find that training improves final-decision quality and induces emergent coordination in participation, speaker selection, and communication, even though the reward evaluates only the final decision.

Abstract: Textual artifacts are sometimes valued not only for the words on the page, but for the human activity involved in producing them. The effort invested in a carefully tailored email can signal genuine interest; composing an apology might involve attending to another person's hurt and deciding how to respond; and requiring a judge to give written reasons may induce more careful deliberation. AI models create what we call a decoupling problem: they make it possible to produce text without undergoing the relevant human activity, severing its connection to values traditionally sustained by that activity. This Article develops a framework for understanding what decoupling puts at stake, and how institutions that use text to make consequential decisions may reshape their practices in response. First, it offers a taxonomy of the grounds for valuing the production process, distinguishing whether that process matters for what it evidences, induces, or helps constitute. Second, it argues that text can function as a kind of boundary object, allowing institutions to rely on the same artifact without resolving disagreements about why the practice is valuable. AI can separate functions previously served by the same practice - a second-order decoupling that brings unresolved questions about the practice's purposes into view. Third, it argues that institutional efforts to repair decoupling may recover some functions without preserving others. Such responses are likely to favor functions that are more legible, whose loss demands immediate attention, or whose stakeholders have greater influence. It therefore calls for more explicit deliberation about which particular functions of a practice to preserve, with meaningful representation for those whose interests might otherwise be overlooked.