Problem
Research questions and friction points this paper is trying to address.
Multi-agent Systems
Failure Attribution
LLMs
Trace Representation
Observability
Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems
🤖 AI Summary
研究提出自适应影响图（AIGs）解决多代理系统中故障定位难题，通过将失败轨迹转换为结构化图并导航以识别关键错误，提高了故障归因准确性。
📝 Abstract
Multi-agent LLM systems are increasingly deployed in real-world applications, where failures can be costly and difficult to localize. Despite growing efforts to automate failure attribution, diagnosing failed runs still largely relies on human engineers. Yet engineers rarely debug complex systems by reading raw logs end to end. Instead, observability tools organize traces around components, actions, and dependencies to support targeted navigation. We hypothesize that modern LLMs can benefit from the same paradigm. To test this hypothesis, we introduce Adaptive Influence Graphs (AIGs), a two-stage agentic framework that first transforms a failed trace into a structured graph and then navigates it to identify the critical error. Across multiple models, we show that richer trace representations consistently improve failure attribution, with adaptive graph construction and agent-directed traversal yielding the strongest results. AIGs establish a new state of the art on Who&When, the standard benchmark for multi-agent failure attribution. This affirms our hypothesis that attribution depends not only on the diagnosing model, but also on how the trace is represented and explored.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Adaptive Influence Graphs
failure attribution
multi-agent systems
trace representation
🔎 Similar Papers
No similar papers found.
