Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: In, Yeonjun, Tanjim, Mehrab, Subramanian, Jayakumar, Kim, Sungchul, Bhattacharya, Uttaran, Kim, Wonjoong, Park, Sangwu, Sarkhel, Somdeb, Park, Chanyoung
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908914497355776
author In, Yeonjun
Tanjim, Mehrab
Subramanian, Jayakumar
Kim, Sungchul
Bhattacharya, Uttaran
Kim, Wonjoong
Park, Sangwu
Sarkhel, Somdeb
Park, Chanyoung
author_facet In, Yeonjun
Tanjim, Mehrab
Subramanian, Jayakumar
Kim, Sungchul
Bhattacharya, Uttaran
Kim, Wonjoong
Park, Sangwu
Sarkhel, Somdeb
Park, Chanyoung
contents Failure attribution is essential for diagnosing and improving multi-agent systems (MAS), yet existing benchmarks and methods largely assume a single deterministic root cause for each failure. In practice, MAS failures often admit multiple plausible attributions due to complex inter-agent dependencies and ambiguous execution trajectories. We revisit MAS failure attribution from a multi-perspective standpoint and propose multi-perspective failure attribution, a practical paradigm that explicitly accounts for attribution ambiguity. To support this setting, we introduce MP-Bench, the first benchmark designed for multi-perspective failure attribution in MAS, along with a new evaluation protocol tailored to this paradigm. Through extensive experiments, we find that prior conclusions suggesting LLMs struggle with failure attribution are largely driven by limitations in existing benchmark designs. Our results highlight the necessity of multi-perspective benchmarks and evaluation protocols for realistic and reliable MAS debugging.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25001
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
In, Yeonjun
Tanjim, Mehrab
Subramanian, Jayakumar
Kim, Sungchul
Bhattacharya, Uttaran
Kim, Wonjoong
Park, Sangwu
Sarkhel, Somdeb
Park, Chanyoung
Artificial Intelligence
Failure attribution is essential for diagnosing and improving multi-agent systems (MAS), yet existing benchmarks and methods largely assume a single deterministic root cause for each failure. In practice, MAS failures often admit multiple plausible attributions due to complex inter-agent dependencies and ambiguous execution trajectories. We revisit MAS failure attribution from a multi-perspective standpoint and propose multi-perspective failure attribution, a practical paradigm that explicitly accounts for attribution ambiguity. To support this setting, we introduce MP-Bench, the first benchmark designed for multi-perspective failure attribution in MAS, along with a new evaluation protocol tailored to this paradigm. Through extensive experiments, we find that prior conclusions suggesting LLMs struggle with failure attribution are largely driven by limitations in existing benchmark designs. Our results highlight the necessity of multi-perspective benchmarks and evaluation protocols for realistic and reliable MAS debugging.
title Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
topic Artificial Intelligence
url https://arxiv.org/abs/2603.25001