Pith. sign in

REVIEW 3 cited by

Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.06882 v1 pith:7HAOEYID submitted 2025-02-08 cs.CL cs.AI

Shengbin Yue , Ting Huang , Zheng Jia , Siyuan Wang , Shujun Liu , Yun Song , Xuanjing Huang , Zhongyu Wei This is my paper
classification cs.CLcs.AI
keywords legalinteractivescenariosdataintroduceslanguagellmsmaser
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) have significantly advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios. This paper introduces a Multi-agent Legal Simulation Driver (MASER) to scalably generate synthetic data by simulating interactive legal scenarios. Leveraging real-legal case sources, MASER ensures the consistency of legal attributes between participants and introduces a supervisory mechanism to align participants' characters and behaviors as well as addressing distractions. A Multi-stage Interactive Legal Evaluation (MILE) benchmark is further constructed to evaluate LLMs' performance in dynamic legal scenarios. Extensive experiments confirm the effectiveness of our framework.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LegalWorld: A Life-Cycle Interactive Environment for Legal Agents

    cs.CL 2026-06 unverdicted novelty 7.0 of 10

    LegalWorld is a life-cycle interactive environment modeling Chinese civil litigation as five causally connected stages grounded in 75,309 judgments, paired with LongJud-Bench for cross-stage agent evaluation.

  2. When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't

    cs.CL 2026-04 unverdicted novelty 7.0 of 10

    VLMs violate their own stated introspective rules for attributing colors to objects in nearly 60% of cases on items with strong color priors, unlike humans who largely follow theirs, revealing miscalibrated self-knowledge.

  3. A Survey on Agent Workflow -- Status and Future

    cs.AI 2025-08 conditional novelty 3.0 of 10

    A review that classifies 24 agent workflow systems along functional and architectural axes and argues for standardization, optimization, and security work.

Pith tools