Conflict-Aware Multi-Agent Reasoning via Signed Graph Modeling

LLM-based multi-agent systems (MAS) seek to improve reasoning by combining diverse perspectives from multiple agents. However, aggregation may overlook supportive, contradictory, and uncertain relations among their responses. As a result, useful dissent can be suppressed, allowing an incorrect majority to dominate the final decision. We introduce SIGMA, a novel Signed Graph-informed Multi-Agent reasoning framework that distinguishes support, contradiction, and uncertainty among responses from black-box LLM agents. SIGMA constructs a signed evidence graph, reassesses disputed relations, and forms reasoning communities while preserving distinct evidence. It then conducts bounded cross-examination between community representatives and adjudicates their evidence without treating community size as a proxy for correctness. Extensive experiments on six benchmark datasets, across multiple LLM backbones and diverse multi-agent configurations, demonstrate that SIGMA consistently outperforms state-of-the-art baselines, achieving notable gains in both accuracy and conflict-resilient performance.