{"paper":{"title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chenyu Zhao, Chetan Bansal, Dan Pei, Minghua Ma, Saravan Rajmohan, Shenglin Zhang, Wenwei Gu, Yihang Lin, Yongqian Sun, Zhimin Chen","submitted_at":"2026-05-09T06:02:08Z","abstract_excerpt":"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 Lay"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Guidance Gate can reliably produce diagnosis-derived guidance that is both evidence-grounded and executable within the unchanged scope of the agent's existing policy, toolset, and execution budget.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PROBE structures runtime telemetry into diagnoses and evidence-grounded guidance, raising recovery rates by 12.45 points over baselines on 257 unresolved software repair and AIOps cases.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"627c1e15d69323dc8cdb3136bdc5da9110d3ac473f22b114745f7ba2a73ea623"},"source":{"id":"2605.08717","kind":"arxiv","version":2},"verdict":{"id":"dcd092c8-14ed-4f8f-b3d1-123d325dbb7c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T00:59:42.570340Z","strongest_claim":"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.","one_line_summary":"PROBE structures runtime telemetry into diagnoses and evidence-grounded guidance, raising recovery rates by 12.45 points over baselines on 257 unresolved software repair and AIOps cases.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Guidance Gate can reliably produce diagnosis-derived guidance that is both evidence-grounded and executable within the unchanged scope of the agent's existing policy, toolset, and execution budget.","pith_extraction_headline":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08717/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T09:02:01.957960Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:35:47.929456Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:31:17.660461Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:50:59.212124Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7ac523fb323834d90cf3d678bdf5b1d59c5b5fd836d41a4fa218e367eea39870"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d34157f3f272412b0cf310d7c7245178c2f32905a6e85fd4b11a60293b26f6b2"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}