arXiv AI
Jul 1
Investigating Multi-Agent Deliberation in Law
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.
L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning
arXiv:2607. 09099v1 Announce Type: new Abstract: While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly structured, knowledge-heavy legal domains remains under-explored.
Related stories
arXiv AI
Aug 5
Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering
arXiv:2608. 01463v2 Announce Type: replace Abstract: Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims.
arXiv AI
Jul 31
Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges
arXiv:2607. 26212v1 Announce Type: cross Abstract: Multi-Agent Debate (MAD) is a promising paradigm for improving the accuracy and robustness of Large Language Model (LLM)-based agentic systems.
arXiv Machine Learning
Sep 22
Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal Research
arXiv:2609.22209v1 Announce Type: cross Abstract: Empirical legal research often relies on turning research questions into structured data extracted from large collections of rulings and judgments. D...
arXiv AI
Jun 16
DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation
arXiv:2601. 05746v2 Announce Type: replace Abstract: Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving.
arXiv AI
Aug 20
A Theory of Post-hoc Debate Judgement
The paper proposes a theory for judging post-hoc debates in AI, focusing on properties like reproducibility, robustness, groundedness, and explainability. It evaluates two debate‑judgement methods—LLM judges and formal computational argumentation semantics—finding similar accuracy but noting that argumentation semantics offers stronger formal guarantees. The study suggests that argumentation semantics is a preferable framework for principled debate judges in AI systems.
arXiv AI
Jun 30
Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning
arXiv:2606. 29425v1 Announce Type: new Abstract: Existing multi-agent debate frameworks suffer from two critical limitations: they rely on static architectures where agent roles and coordination patterns are fixed at design time, and they require instantiating multiple model copies, incurring substantial computational overhead.
arXiv AI
Aug 24
Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
The paper introduces a method to improve test-time scaling (TTS) for large language models by using multi-agent systems (MAS) to split long reasoning chains into manageable contexts. A new dataset, M500, containing 500 multi-agent collaborative reasoning traces, is used to fine‑tune open‑source models, enabling them to learn collaborative patterns and outperform their base versions. An adaptive scaling strategy with a "CEO" agent is proposed to dynamically guide reasoning depth, and experiments in the AgentVerse framework confirm the effectiveness of the approach.
arXiv Computation and Language
Aug 25
Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognition
Meta-Moderator is a learnable framework that treats moderation as a meta‑cognitive process, monitoring debate utility, controlling deliberation, and adjudicating final answers. It is trained independently of the debaters through outcome‑driven policy optimization, allowing dynamic regulation of debate rather than relying on fixed budgets or untrained judges. Across five benchmarks, Meta‑Moderator outperforms common decision layers, transfers across tasks and system configurations, and selectively allocates debate to reduce mis‑aggregation after informative hypotheses appear.
arXiv AI
Jun 4
Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal
arXiv:2606. 04223v1 Announce Type: new Abstract: Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation.
arXiv Computation and Language
Aug 25
From Diagnosis to Redesign: Using Quantitative Ethnography to Improve Multi-Agent LLM Reasoning
arXiv:2608.22566v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems are designed to improve reasoning by decomposing tasks across multiple agents with specialized functions...
arXiv Computation and Language
Sep 24
LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning
LEGO is a dual‑module framework that combines a Legal Expert GraphRAG system with an expert Chain‑of‑Thought approach to enhance complex legal reasoning. The GraphRAG component uses an expert‑annotated civil code graph and a greedy normative‑coverage retrieval algorithm to extract relevant provision subgraphs, while the Chain‑of‑Thought module structures retrieved provisions and case facts into a Provision‑Fact‑Conclusion reasoning flow. Using a Qwen3‑8B backbone, LEGO achieves 40.53% exact‑match accuracy on LawExamQA_Civil, surpassing baseline RAG and CoT models and matching larger models on multi‑hop and open‑ended benchmarks, with ablation studies confirming the complementary benefits of both modules.