Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling

TL;DR

The paper introduces SIGMA, a signed graph-based framework for multi-agent reasoning that explicitly models conflicts and trust, leading to more accurate and conflict-resilient predictions across various benchmarks.

Contribution

SIGMA is the first framework to incorporate explicit conflict and trust modeling via signed graphs in multi-agent reasoning, improving robustness and accuracy.

Findings

SIGMA outperforms state-of-the-art baselines on six benchmark datasets.

It achieves significant gains in accuracy and conflict resilience.

The framework is effective across multiple LLM backbones and configurations.

Abstract

LLM-based multi-agent systems (MAS) have demonstrated strong reasoning and decision-making capabilities that consistently surpass those of single LLM agents. However, their performance often suffers from naive aggregation mechanisms that assume uniformly cooperative interactions. Upon close inspection, we observe that existing graph-based MAS frameworks (1) propagate errors when conflicting signals arise without control, and (2) lack explicit modeling of conflicting inter-agent relations as well as structural awareness, failing to identify reliable interaction patterns. To bridge this gap, we introduce SIGMA, a novel SIgned Graph-informed Multi-Agent reasoning framework that explicitly captures trust, conflict, and neutral relations among agents via a signed relational graph. Specifically, given a query, SIGMA first selects a set of relevant and diverse agents, then constructs a structured signed interaction graph with confidence-weighted edges. Reasoning proceeds through conflict-aware signed message passing, which reinforces information from trustworthy agents while suppressing conflicting signals, and terminates with a structure- and conflict-aware weighted aggregation to yield globally consistent and conflict-resilient predictions. 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.