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

arXiv:2608.29646 · cs.AI, cs.MA · Submitted 2026-08-30 · Read on arXiv

cs.AI, cs.MA

Submitted: 2026-08-30

Updated: 2026-08-30

Terminology

• Accuracy — 34× in this paper · explained in 1 episode
• Failure Attribution — 22× in this paper
• Multi-Agent System — 14× in this paper · explained in 6 episodes
• Trace — 14× in this paper · explained in 2 episodes
• Data Augmentation — 13× in this paper · explained in 7 episodes
• Multi-Agent Systems — 13× in this paper
• Transformer — 13× in this paper · explained in 2 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• Generalization — 10× in this paper · explained in 13 episodes
• Embeddings — 9× in this paper · explained in 2 episodes
• Robustness — 7× in this paper · explained in 5 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Hallucination — 6× in this paper · explained in 4 episodes
• Latent Space — 6× in this paper · explained in 7 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• Reconstruction Error — 4× in this paper · explained in 2 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Computational overhead — 3× in this paper · explained in 2 episodes
• Adjacency Matrix — 2× in this paper · explained in 1 episode
• Agentic System — 2× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Causal Inference — 2× in this paper · explained in 4 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Meeting of the Association for Computational Linguistics — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Zero-Shot Generalization — 2× in this paper · explained in 5 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Dynamic Time Warping (DTW) — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• In International Conference on Learning Representations — 1× in this paper
• Information Leakage — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Mean Squared Error — 1× in this paper
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Negative Log-Likelihood — 1× in this paper
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution
• Why Do Multi-Agent LLM Systems Fail?
• AutoAgents: A Framework for Automatic Agent Generation
• A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• TRAIL: Trace Reasoning and Agentic Issue Localization
• Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis
• MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
• Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
• Evaluating LLMs at Detecting Errors in LLM Responses
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• Aegis: Automated Error Generation and Attribution for Multi-Agent Systems
• LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
• Process Reward Model with Q-Value Rankings
• Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference
• Generative Agents: Interactive Simulacra of Human Behavior
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
• Benchmarking LLMs' Swarm intelligence
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
• AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?

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