# From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems

arXiv: https://arxiv.org/abs/2602.23701 · HTML: https://mlsanity.com/paper/2602.23701/

## Key facts

- Cited by 19 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 15 of its 34 references that are in the map.
- First posted on arXiv 27 Feb 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, 15 of 15)

- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?](https://mlsanity.com/paper/2407.15711/) (2024)
- [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025)
- [Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories](https://mlsanity.com/paper/2506.18824/) (2025)
- [Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds](https://mlsanity.com/paper/2310.13255/) (2023)
- [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)
- [GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search](https://mlsanity.com/paper/2510.10581/) (2025)

## Built on by (most cited first, 19 of 19)

- [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026)
- [FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search](https://mlsanity.com/paper/2606.00765/) (2026)
- [Tracing Agentic Failure from the Flow of Success](https://mlsanity.com/paper/2607.12747/) (2026)
- [MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals](https://mlsanity.com/paper/2605.07509/) (2026)
- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)
- [MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems](https://mlsanity.com/paper/2605.28732/) (2026)
- [CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring](https://mlsanity.com/paper/2605.19240/) (2026)
- [AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems](https://mlsanity.com/paper/2609.08572/) (2026)
- [TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling](https://mlsanity.com/paper/2605.23966/) (2026)
- [LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories](https://mlsanity.com/paper/2608.15242/) (2026)
- [ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems](https://mlsanity.com/paper/2608.10646/) (2026)
- [Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution](https://mlsanity.com/paper/2608.18575/) (2026)
- [Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay](https://mlsanity.com/paper/2608.29228/) (2026)
- [DAAF: From Failure Localization to Editable System Assets in LLM Agents](https://mlsanity.com/paper/2609.32498/) (2026)
- [Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis](https://mlsanity.com/paper/2609.38851/) (2026)
- [ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems](https://mlsanity.com/paper/2610.11334/) (2026)
- [Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2610.11600/) (2026)
- [Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level Labels](https://mlsanity.com/paper/2610.13105/) (2026)
- [BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems](https://mlsanity.com/paper/2610.18780/) (2026)

## Abstract (arXiv)

LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting, costly replays, or supervised fine-tuning, typically treat execution logs as flat sequences. This linear perspective fails to disentangle the intricate causal links inherent to MAS, leading to weak observability and ambiguous responsibility boundaries. To address these challenges, we propose CHIEF, a novel framework that transforms chaotic trajectories into a structured hierarchical causal graph. It then employs hierarchical oracle-guided backtracking to efficiently prune the search space via sybthesized virtual oracles. Finally, it implements counterfactual attribution via a progressive causal screening strategy to rigorously distinguish true root causes from propagated symptoms. Experiments on Who&When benchmark show that CHIEF outperforms eight strong and state-of-the-art baselines on both agent- and step-level accuracy. Ablation studies further confirm the critical role of each proposed module.