# VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems

arXiv: https://arxiv.org/abs/2605.17467 · HTML: https://mlsanity.com/paper/2605.17467/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 36 of its 38 references that are in the map.
- First posted on arXiv 17 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts](https://mlsanity.com/paper/2110.01799/) (2021)
- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails](https://mlsanity.com/paper/2501.09004/) (2025)
- [GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning](https://mlsanity.com/paper/2406.09187/) (2024)
- [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025)
- [Latent Collaboration in Multi-Agent Systems](https://mlsanity.com/paper/2511.20639/) (2025)
- [G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems](https://mlsanity.com/paper/2502.11127/) (2025)
- [AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security](https://mlsanity.com/paper/2601.18491/) (2026)
- [Deep Graph Anomaly Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2409.09957/) (2024)
- [SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures](https://mlsanity.com/paper/2110.07518/) (2021)
- [GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling](https://mlsanity.com/paper/2505.19234/) (2025)
- [Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis](https://mlsanity.com/paper/2509.13782/) (2025)
- [Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution](https://mlsanity.com/paper/2510.04886/) (2025)
- [Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation](https://mlsanity.com/paper/2603.25001/) (2026)
- [GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search](https://mlsanity.com/paper/2510.10581/) (2025)
- [Aegis: Automated Error Generation and Attribution for Multi-Agent Systems](https://mlsanity.com/paper/2509.14295/) (2025)
- [Rethinking the Reliability of Multi-agent System: A Perspective from Byzantine Fault Tolerance](https://mlsanity.com/paper/2511.10400/) (2025)

## Built on by (most cited first, 5 of 5)

- [Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence](https://mlsanity.com/paper/2608.12895/) (2026)
- [ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems](https://mlsanity.com/paper/2608.10646/) (2026)
- [DeFA: Dependency-Guided Failure Attribution for LLM Agents](https://mlsanity.com/paper/2610.01256/) (2026)
- [Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault](https://mlsanity.com/paper/2609.32802/) (2026)
- [Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows](https://mlsanity.com/paper/2609.34017/) (2026)

## Abstract (arXiv)

Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing approaches, such as direct prediction of agent-error pairs and agent-first failure attribution, rely on local logs of agents and miss global failures that only manifest over full interaction trajectories, such as cross-step inconsistencies and inter-agent coordination errors. Moreover, directly predicting failures induces a large combinatorial search space, hindering fine-grained attribution. To address these challenges, we propose VerifyMAS, a hypothesis verification framework for agent failure attribution. Instead of directly predicting faulty agents and error types, VerifyMAS formulates and verifies failure hypotheses against full trajectories. This verification-based approach decomposes attribution into trajectory-level error validation and fine-grained agent localization, providing an error-first attribution approach that captures global failure patterns while substantially reducing the search space. We further introduce a hypothesis-based data construction strategy grounded in a structured error taxonomy and fine-tune a specialized LLM verifier model for trajectory-level failure verification and agent attribution. Experiments on Aegis-Bench and Who&When show that VerifyMAS consistently improves diverse backbone models, including open-source Qwen and API-based GPT models, outperforming prior methods without sacrificing inference efficiency for long multi-agent trajectories.