SOURCE-LINKED INTELLIGENCE

Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to execution failures. Accurate failure attribution is therefore critical for improving agent reliability. Existing topology- and spectrum-based methods exploit trajectory structures but often overlook fine-grained semantics, while LLM-based attribution methods capture semantic cues but suffer from long-context degradation over lengthy trajectories. To address these challenges, we propose DUOTRACE, a plug-and-play detection filter for LLM-based f

Read original source ↗ Open in workspace

recordType

paper

region

Global