{"paper":{"title":"RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aaditya Bhatia, Ahmed E. Hassan, Arthur Leung, Boyuan Chen, Chengzong Zhao, Chong Chun Yong, Dayi Lin, Gopi Krishnan Rajbahadur, Gustavo A. Oliva, Haoxiang Zhang, Yihao Chen, Zhilong Chen","submitted_at":"2025-08-03T02:34:16Z","abstract_excerpt":"Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present RepoForge, an autonomous, end-to-end pipeline that generates, evaluates, and trains SWE agents at scale. Our key contributions include: (1) RepoForge-8B-Agent, achieving 17.4\\% on SWE-Bench-Verified~\\citep{swebench_verified2024}, establishing new state-of-the-art for $\\leq$8B non-thinking LLMs; (2) 7,304 executable environments auto-generated from real GitHub commits with zero manual intervention; (3) 14$\\times$ sto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01550","kind":"arxiv","version":2},"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/2508.01550/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"}