SOURCE-LINKED INTELLIGENCE

Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

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-st

Read original source ↗ Open in workspace

recordType

paper

region

Global