Go to AAMAS 2026 Conference homepageGraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search
Keywords: Large Language Model, Multi-agent Systems, Graph, Multi-agent Communication, Communication Topology
Abstract: Multi-agent systems powered by Large Language Models excel at complex tasks through coordinated collaboration, yet they face high failure rates in multi-turn deep search scenarios. Existing temporal attribution methods struggle to accurately diagnose root causes, particularly when errors propagate across multiple agents. Attempts to automate failure attribution by analyzing action sequences remain ineffective due to their inability to account for information dependencies that span agents. This paper identifies two core challenges in diagnosing failures: (i) distinguishing failure symptoms from their underlying causes when errors spread through long dependency chains, and (ii) capturing causal relationships that go beyond simple temporal order. To address these issues, we introduce GraphTracer, a framework that redefines failure attribution through information flow analysis. GraphTracer constructs Information Dependency Graphs (IDGs) to explicitly capture how agents reference and build on prior outputs. It localizes root causes by tracing through these dependency structures instead of relying on temporal sequences. GraphTracer also uses graph-aware synthetic data generation to target critical nodes, creating realistic failure scenarios. Evaluations on the Who\&When benchmark and integration into production systems demonstrate that GraphTracer-8B achieves up to 18.18\% higher attribution accuracy compared to state-of-the-art models and enables 4.8\% to 14.2\% performance improvements in deployed multi-agent frameworks, establishing a robust solution for multi-agent system debugging.
Area: Generative and Agentic AI (GAAI)
Generative A I: I acknowledge that I have read and will follow this policy.
Submission Number: 1823
Loading