Saved in:
Bibliographic Details
Main Authors: Barke, Shraddha, Goyal, Arnav, Khare, Alind, Singh, Avaljot, Nath, Suman, Bansal, Chetan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.02475
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912869057036288
author Barke, Shraddha
Goyal, Arnav
Khare, Alind
Singh, Avaljot
Nath, Suman
Bansal, Chetan
author_facet Barke, Shraddha
Goyal, Arnav
Khare, Alind
Singh, Avaljot
Nath, Suman
Bansal, Chetan
contents AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a novel benchmark of 115 failed trajectories spanning structured API workflows, incident management, and open-ended web/file tasks. Each trajectory is annotated with a critical failure step and a category from a grounded-theory derived, cross-domain failure taxonomy. To mitigate the human cost of failure attribution, we present AGENTRX, an automated domain-agnostic diagnostic framework that pinpoints the critical failure step in a failed agent trajectory. It synthesizes constraints, evaluates them step-by-step, and produces an auditable validation log of constraint violations with associated evidence; an LLM-based judge uses this log to localize the critical step and category. Our framework improves step localization and failure attribution over existing baselines across three domains.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02475
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
Barke, Shraddha
Goyal, Arnav
Khare, Alind
Singh, Avaljot
Nath, Suman
Bansal, Chetan
Artificial Intelligence
AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a novel benchmark of 115 failed trajectories spanning structured API workflows, incident management, and open-ended web/file tasks. Each trajectory is annotated with a critical failure step and a category from a grounded-theory derived, cross-domain failure taxonomy. To mitigate the human cost of failure attribution, we present AGENTRX, an automated domain-agnostic diagnostic framework that pinpoints the critical failure step in a failed agent trajectory. It synthesizes constraints, evaluates them step-by-step, and produces an auditable validation log of constraint violations with associated evidence; an LLM-based judge uses this log to localize the critical step and category. Our framework improves step localization and failure attribution over existing baselines across three domains.
title AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
topic Artificial Intelligence
url https://arxiv.org/abs/2602.02475