Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge

The paper introduces AgentAuditor, a method that improves multi-agent large language model (LLM) reasoning by structuring agent outputs into a Reasoning Tree that captures agreements and divergences, rather than relying on simple majority voting. AgentAuditor resolves conflicts by comparing evidence at key divergence points, enabling efficient localized verification. The authors also propose Anti-Consensus Preference Optimization (ACPO) to train the adjudicator with evidence-verified supervision, reducing reliance on misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently outperforms majority voting, achieving up to 5% absolute accuracy gains while remaining token‑efficient.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• benchmarks