Search papers, labs, and topics across Lattice.
This paper addresses the challenge of failure localization in LLM-based multi-agent systems, where diagnosing which agent is responsible for a failure and identifying the point of irreversible misdirection is complex due to inter-agent dependencies. The authors introduce AgentLocate, a novel framework that utilizes an LLM-based judging mechanism combined with multi-perspective verification from independent evaluators, enhancing the accuracy of failure attribution through a confidence-aware aggregation strategy. Experimental evaluations demonstrate that AgentLocate significantly outperforms existing methods in both identifying responsible agents and pinpointing failure steps while maintaining efficiency in token usage and runtime.
AgentLocate reveals not just which agent failed, but also the critical moment when the system first went off track, outperforming traditional methods in efficiency and accuracy.
Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new challenges in diagnosing system-level failures. When an execution fails, identifying which agent is responsible and at what point the trajectory first becomes irreversibly misdirected is difficult due to long-horizon interactions and tightly coupled agent behaviors. In this paper, we study the problem of failure localization in LLM-based multi-agent systems and present AgentLocate, a framework that attributes failures to both a specific agent and the earliest decisive step. AgentLocate combines an LLM-based judging mechanism with multi-perspective verification by independent evaluators, whose assessments are aggregated using a confidence-aware strategy. The resulting feedback is further used to adapt the judge through lightweight fine-tuning, improving attribution quality. We evaluate AgentLocate on two complementary benchmarks covering diverse tasks, agent configurations, and trajectory lengths. Experimental results show that AgentLocate consistently outperforms existing failure localization methods in identifying both responsible agents and failure steps, while remaining efficient in terms of token usage and running time.
