Civil litigation is inherently a life-cycle process: what a lawyer drafts on day one constrains what unfolds at trial months later. Yet existing legal benchmarks evaluate isolated subtasks, and prior legal-agent simulators reinitialize each scenario from shared ground truth, leaving cross-stage causal dependencies unmodeled.
arXiv:2606.09389v2 Announce Type: replace Abstract: As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the reliability of their open-ended legal responses...
Legal Research Bench (LRB) is a new benchmark comprising 413 open-ended U.S. legal research questions, each paired with a gold answer, supporting authorities, and a binary grading rubric. The study evaluates thirteen advanced language‑model agents using web search, case‑law search, page parsing, and retrieval tools, scoring responses only when all required criteria are met and cited authorities verify. Results show that even the best model, Claude Opus 4.8, achieves full correctness on only 42.9% of questions, with performance varying by legal area and task complexity, and no clear link between more tool calls or inference cost and higher accuracy.
arXiv:2606. 04602v1 Announce Type: new Abstract: As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products -- yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes.
As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products -- yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes. We address each.
arXiv:2606. 30906v1 Announce Type: new Abstract: Artificial Intelligence is increasingly applied to the field of law, and has the potential to increase access to justice.
ProMediConv is a new benchmarking framework for evaluating proactive conversational agents in legal dispute mediation. It models mediation as a multi-stage, party-aware dialogue that incorporates 11 mediation strategies and four party behavior pattern states, and it is built on 972 real-world cases with utterance-level annotations. The framework introduces a fine-grained metric, MAD (Mean Attribute Difference), to capture shifts in party behavior throughout the dialogue, and provides a comprehensive benchmark with diverse models and a tailored baseline, ProMediAgent.
arXiv:2606. 18699v1 Announce Type: cross Abstract: Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet their performance on jurisdiction-specific legal reasoning remains underexplored.
arXiv:2606. 22737v2 Announce Type: replace Abstract: Before letting an agent operate over real context, can you prove it used the right evidence?
arXiv:2606. 18021v1 Announce Type: new Abstract: AI systems deployed in legal workflows hallucinate at rates that aggregate metrics report at ~52%, but this average conceals where errors concentrate and in which direction they run, leaving compliance officers without an actionable signal for trustworthy deployment.
LexIssue introduces a benchmark for identifying disputed legal issues in Chinese civil litigation, comprising 430 real‑world cases and 1,303 expert‑annotated issues. The dataset is built around a hierarchical schema that links free‑form issue descriptions to structured legal categories, enabling two complementary tasks: issue generation and issue classification. A retrieval‑augmented knowledge base covering 27 causes of action and 441 issue entries is provided, and experiments show that incorporating this knowledge consistently improves model performance on the tasks.
arXiv:2605.25920v2 Announce Type: replace Abstract: While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constra...
arXiv:2608. 13712v1 Announce Type: cross Abstract: Deposition training requires attorneys to manage dynamic witness behavior, yet legal-AI evaluations largely focus on factual accuracy, reasoning, or response-level plausibility.