Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems
cs.AI
Submitted: 2026-08-25
Updated: 2026-08-25
Code: https://github.com/Arize-ai/phoenix
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution
- AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
- From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
- Talk like a Graph: Encoding Graphs for Large Language Models
- Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis
- Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
- Knowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces
- CodeTracer: Towards Traceable Agent States
- Towards Self-Improving Error Diagnosis in Multi-Agent Systems
- Lost in the Middle: How Language Models Use Long Contexts
- MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals
- Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference
- VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
- FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search
- Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
- Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
- From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
- Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems
- CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems
- AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection