LexAgentHallu is a new benchmark that profiles hallucinations in legal agents across multi-step interactions. It contains 3,414 instances spanning 17 legal categories and 6 task types, each annotated with a dual-layer taxonomy of 7 high-level and 27 fine-grained hallucination categories. The benchmark introduces fine-grained metrics to quantify and localize failures along an agent’s execution path, revealing patterns such as the Right-Answer-Wrong-Reason effect and clustered hallucination subclasses.
As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning errors cascade into fabricated holdings and misci...
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.
arXiv:2601.22984v3 Announce Type: replace Abstract: Diagnosing failure patterns in Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evalu...
The paper argues that hallucinations by legal language models should be judged as failures of legal warrant rather than mere factual or citation errors. It defines claim-authority warrant as a context-sensitive relationship between a legal claim and applicable, current authority, and proposes that evaluating warrant can uncover failures missed by traditional accuracy or citation metrics. The authors outline a pilot study, benchmark specifications, and a research agenda to assess whether legal AI systems’ claims are properly licensed by law.
arXiv:2608. 14210v1 Announce Type: cross Abstract: Hallucination is a major challenge for retrieval-augmented generation (RAG) systems in the legal domain, where ungrounded answers can lead to serious consequences.
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.
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. 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.
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...
The paper introduces SCHEMA, a topology‑aware evaluation framework designed to assess hallucinations in large language model agents used for scientific research. SCHEMA builds scientific concept graphs from benchmark seeds and literature evidence, then generates graph‑grounded tasks such as claim verification, multi‑hop reasoning, open‑ended explanation, and experimental code generation. It evaluates agents using a trajectory hallucination pipeline that assigns a topology‑weighted severity score and a multi‑agent counterfactual attribution module that identifies the causal mechanisms behind failures. The study finds that hallucinations tend to cluster around highly connected knowledge hubs and that a model’s final accuracy can be misleading, as correct answers may arise from structurally flawed reasoning. "whyItMatters":"The findings highlight that terminal accuracy alone is insufficient for high‑stakes scientific applications, underscoring the need for mechanism‑level evaluation grounded in knowledge topology."
arXiv:2607. 18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.
arXiv:2607. 17883v1 Announce Type: cross Abstract: Enterprises will not deploy AI agents they cannot trust, and the most-cited reason for distrust is hallucination: confident, fluent output that is simply not true.