Papers
arxiv:2605.06788

Conformal Agent Error Attribution

Published on May 7
· Submitted by
Jesse Cresswell
on May 12
Authors:
,
,
,
,

Abstract

A conformal prediction framework is proposed for error attribution in multi-agent systems, enabling precise error isolation and automated recovery through contiguous sequence predictions.

AI-generated summary

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.

Community

conformal-agent-error-attribution-1
If an agent fails a task, rather than start over from the beginning, it is more efficient to roll back to the agent's state just before the decisive error occurred. We use conformal prediction to isolate the decisive error with high confidence.

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.06788
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.06788 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.06788 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.06788 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.