Conformal Agent Error Attribution

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Naihe, Sui, Yi, Hou, Shiyi, Wu, Ga, Cresswell, Jesse C.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911658838851584
author Feng, Naihe
Sui, Yi
Hou, Shiyi
Wu, Ga
Cresswell, Jesse C.
author_facet Feng, Naihe
Sui, Yi
Hou, Shiyi
Wu, Ga
Cresswell, Jesse C.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06788
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Conformal Agent Error Attribution
Feng, Naihe
Sui, Yi
Hou, Shiyi
Wu, Ga
Cresswell, Jesse C.
Machine Learning
Multiagent Systems
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.
title Conformal Agent Error Attribution
topic Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2605.06788