Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Chenyu, Zhang, Shenglin, Lin, Yihang, Gu, Wenwei, Chen, Zhimin, Sun, Yongqian, Pei, Dan, Bansal, Chetan, Rajmohan, Saravan, Ma, Minghua
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911666692685824
author Zhao, Chenyu
Zhang, Shenglin
Lin, Yihang
Gu, Wenwei
Chen, Zhimin
Sun, Yongqian
Pei, Dan
Bansal, Chetan
Rajmohan, Saravan
Ma, Minghua
author_facet Zhao, Chenyu
Zhang, Shenglin
Lin, Yihang
Gu, Wenwei
Chen, Zhimin
Sun, Yongqian
Pei, Dan
Bansal, Chetan
Rajmohan, Saravan
Ma, Minghua
contents Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not convert heterogeneous runtime evidence into grounded, bounded recovery guidance for a subsequent attempt. We present PROBE, a failure-anchored framework for structured recovery in software engineering agents. PROBE organizes failed-run telemetry into structured evidence, structured diagnosis, and bounded recovery guidance through a Telemetry Layer, a Diagnosis Layer, and a Guidance Gate. The Telemetry Layer preserves fine-grained runtime signals, the Diagnosis Layer fuses cross-signal evidence into grounded diagnoses, and the Guidance Gate produces diagnosis-derived guidance only when it is evidence-grounded, actionable, and within the scope of agent-side behavior. We evaluate PROBE across three settings: repository-level software repair, enterprise workflow recovery, and AIOps service mitigation. On 257 initially unresolved cases, PROBE achieves 65.37% Top-1 diagnosis accuracy and a 21.79% recovery rate, outperforming the strongest non-PROBE baseline by 43.58 and 12.45 percentage points. The results reveal a diagnosis-recovery gap: accurate diagnosis is necessary but insufficient unless translated into bounded guidance that a subsequent attempt can execute and verify. Beyond controlled evaluation, a Microsoft IcM prototype shows that PROBE can attach as a non-intrusive side channel to existing service-diagnosis workflows without changing the agent policy, toolset, or execution budget. These results suggest that telemetry-grounded, failure-anchored recovery can improve post-failure recoverability under realistic engineering constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08717
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents
Zhao, Chenyu
Zhang, Shenglin
Lin, Yihang
Gu, Wenwei
Chen, Zhimin
Sun, Yongqian
Pei, Dan
Bansal, Chetan
Rajmohan, Saravan
Ma, Minghua
Software Engineering
Artificial Intelligence
Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not convert heterogeneous runtime evidence into grounded, bounded recovery guidance for a subsequent attempt. We present PROBE, a failure-anchored framework for structured recovery in software engineering agents. PROBE organizes failed-run telemetry into structured evidence, structured diagnosis, and bounded recovery guidance through a Telemetry Layer, a Diagnosis Layer, and a Guidance Gate. The Telemetry Layer preserves fine-grained runtime signals, the Diagnosis Layer fuses cross-signal evidence into grounded diagnoses, and the Guidance Gate produces diagnosis-derived guidance only when it is evidence-grounded, actionable, and within the scope of agent-side behavior. We evaluate PROBE across three settings: repository-level software repair, enterprise workflow recovery, and AIOps service mitigation. On 257 initially unresolved cases, PROBE achieves 65.37% Top-1 diagnosis accuracy and a 21.79% recovery rate, outperforming the strongest non-PROBE baseline by 43.58 and 12.45 percentage points. The results reveal a diagnosis-recovery gap: accurate diagnosis is necessary but insufficient unless translated into bounded guidance that a subsequent attempt can execute and verify. Beyond controlled evaluation, a Microsoft IcM prototype shows that PROBE can attach as a non-intrusive side channel to existing service-diagnosis workflows without changing the agent policy, toolset, or execution budget. These results suggest that telemetry-grounded, failure-anchored recovery can improve post-failure recoverability under realistic engineering constraints.
title Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2605.08717