首页 > AI前沿 > InvestigationWorlds: An Agentic Environment for Legal Investigation

InvestigationWorlds: An Agentic Environment for Legal Investigation

arXiv自然语言 2026-10-03 06:59 6 阅读 查看原文

We introduce InvestigationWorlds, an agentic environment for legal investigation.

We build on an underused artifact of U.S. civil litigation: the summary judgment motion.

This motion relies upon a record composed of real evidence exhibits, and results in a court-adopted hypothesis that is treated as ground truth for the purposes of deciding the motion.

Environment Construction

Each environment is built from a real U.S. Federal Court case retrieved from Public Access to Court Electronic Records (PACER) and augmented by an attorney-validated generation pipeline that synthesizes role-tagged documents around the original record.

Corpus Characteristics

The resulting corpus admits multiple coherent factual readings, only one of which matches the court-adopted hypothesis.

Evaluation

Evaluating on 100 cases, we find agents often commit to incorrect hypotheses despite retrieving relevant evidence, struggling to distinguish the court-adopted hypothesis from alternative hypotheses.