{"paper":{"title":"ProcBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chaoyi Xue, Chenbo Liu, Dong Sun, Jiawei He, Jie Jia, Xikai Yang, Yapeng Song","submitted_at":"2026-05-18T08:34:48Z","abstract_excerpt":"Existing benchmarks for LLM coding agents mainly evaluate final outcomes, such as task completion, compilation success, and test pass rates. While these metrics are useful for measuring end-task capability, they provide limited visibility into how an execution unfolds and often miss recurrent process-level failures that arise during multi-step operation. We present ProcBench, a benchmark-oriented framework for evaluating coding-agent trajectories through process defects and control preservation. ProcBench organizes execution failures into a reusable ontology, standardizes heterogeneous logs in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20251","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.20251/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}