# Towards Self-Improving Error Diagnosis in Multi-Agent Systems

arXiv: https://arxiv.org/abs/2604.17658 · HTML: https://mlsanity.com/paper/2604.17658/

## Key facts

- Cited by 4 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 26 of its 40 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 26 of 26)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025)
- [Self-evolving Agents with reflective and memory-augmented abilities](https://mlsanity.com/paper/2409.00872/) (2024)
- [EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems](https://mlsanity.com/paper/2510.13220/) (2025)
- [The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis](https://mlsanity.com/paper/2311.00237/) (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)
- [QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management](https://mlsanity.com/paper/2512.12967/) (2025)
- [Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain](https://mlsanity.com/paper/2603.02218/) (2026)
- [Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring](https://mlsanity.com/paper/2406.19949/) (2024)
- [Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time](https://mlsanity.com/paper/2502.19230/) (2025)

## Built on by (most cited first, 4 of 4)

- [Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.29790/) (2026)
- [DeFA: Dependency-Guided Failure Attribution for LLM Agents](https://mlsanity.com/paper/2610.01256/) (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)

Large Language Model (LLM)-based Multi-Agent Systems (MAS) enable complex problem-solving but introduce significant debugging challenges, characterized by long interaction traces, inter-agent dependencies, and delayed error manifestation. Existing diagnostic approaches often rely on expensive expert annotation or ''LLM-as-a-judge'' paradigms, which struggle to pinpoint decisive error steps within extended contexts. In this paper, we introduce ErrorProbe, a self-improving framework for semantic failure attribution that identifies responsible agents and the originating error step. The framework operates via a three-stage pipeline: (1) operationalizing the MAS failure taxonomy to detect local anomalies, (2) performing symptom-driven backward tracing to prune irrelevant context, and (3) employing a specialized multi-agent team (Strategist, Investigator, Arbiter) to validate error hypotheses through tool-grounded execution. Crucially, ErrorProbe maintains a verified episodic memory that updates only when error patterns are confirmed by executable evidence, without the need for annotation. Experiments across the TracerTraj and Who&When benchmarks demonstrate that ErrorProbe significantly outperforms baselines, particularly in step-level localization, while the verified memory enables robust cross-domain transfer without retraining.