DeFA: Dependency-Guided Failure Attribution for LLM Agents

DeFA is a dependency-guided framework that attributes failures in large language model agents by constructing an event dependency graph and a failure propagation graph from protocol relations and semantic dependencies. It identifies violating events, traces their sources and effects, and determines the decisive error, responsible agent, and error category. The method supports long trajectories through segmentation and has shown superior accuracy on text, image, and video tasks, while its diagnostic feedback can improve agent performance on subsequent tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• computer-vision
• multimodal