EPS
← All batches·2605.06788

Conformal Agent Error Attribution

topic: general_safetytop score: 50released: 2026-05-11first surfaced: 2026-05-11arXivPDFnew_research2026-05-11

Authors: Naihe Feng, Yi Sui, Shiyi Hou et al.

arXiv · PDF

Summary

The authors tackle error attribution in multi-agent systems (MAS) built from large language models, where failures leave long interaction traces and it's hard to pinpoint which step went wrong. They use conformal prediction (a framework that gives finite-sample, distribution-free coverage guarantees) to predict contiguous subsequences of the agent trajectory that likely contain the error, enabling automated rollback and recovery.

Main takeaways:

  • Standard conformal prediction doesn't handle sequential data well; the authors introduce filtration-based conformal prediction tailored to agent trajectories.
  • Their method predicts contiguous sequence intervals (not arbitrary sets), which makes recovery practical—you can roll back to a specific earlier state.
  • The approach is model-agnostic and provides principled uncertainty quantification for error localization.
  • Experiments show errors can be precisely isolated, and agents can use the prediction sets to roll back and correct their own mistakes.

Relevance

Tangential — this is about multi-agent debugging, not about installing or understanding personas. The only loose connection is that both involve reasoning about "where" in a trajectory a certain behavior emerges, but the techniques and goals are quite different from my fine-tuning and steering work.

Abstract

arXiv:2605.06788v1 Announce Type: new Abstract: When multi-agent systems (MAS) fail, identifying where the decisive error occurred is the first step for automated recovery to an earlier state. Error attribution remains a fundamental challenge due to the long interaction traces that large language model-based MAS generate. This paper presents a framework for error attribution based on conformal prediction (CP) which provides finite-sample, distribution-free coverage guarantees. We introduce new algorithms for filtration-based CP designed for sequential data such as agent trajectories. Unlike existing CP algorithms, our approach predicts sets that are contiguous sequences to enable efficient recovery and debugging. We verify our theoretical guarantees on a variety of agents and datasets, show that errors can be precisely isolated, then use prediction sets to rollback MAS to correct their own errors. Our overall approach is model-agnostic, and offers a principled uncertainty layer for MAS error attribution. We release code at https://github.com/layer6ai-labs/conformal-agent-error-attribution.