SOURCE-LINKED INTELLIGENCE

Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Failures in agentic AI systems can arise from interactions among messages exchanged by multiple large language model (LLM) agents. Pointwise attribution cannot distinguish a jointly necessary repair from alternative singleton repairs. We formulate Minimal Repair Family Recovery (MRFR): recovering all inclusion-minimal event sets whose counterfactual replay restores task success within a declared size bound. We propose Graph-Constrained Joint Replay (GCJR), which slices failure-relevant events from an execution dependency graph, constructs graph-feasible singleton and pair candidates, and verif

Read original source ↗ Open in workspace

recordType

paper

region

Global