{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/swe-dev-evaluating-and-training-autonomous","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","arxiv_id":"2505.16975","date":"2025-05-22","proceeding":null,"authors":["Yaxin Du","Yuzhu Cai","Yifan Zhou","Cheng Wang","Yu Qian","Xianghe Pang","Qian Liu","Yue Hu","Siheng Chen"],"abstract":"Large Language Models (LLMs) have shown strong capability in diverse software engineering tasks, e.g. code completion, bug fixing, and document generation. However, feature-driven development (FDD), a highly prevalent real-world task that involves developing new functionalities for large, existing codebases, remains underexplored. We therefore introduce SWE-Dev, the first large-scale dataset (with 14,000 training and 500 test samples) designed to evaluate and train autonomous coding systems on real-world feature development tasks. To ensure verifiable and diverse training, SWE-Dev uniquely provides all instances with a runnable environment and its developer-authored executable unit tests. This collection not only provides high-quality data for Supervised Fine-Tuning (SFT), but also enables Reinforcement Learning (RL) by delivering accurate reward signals from executable unit tests. Our extensive evaluations on SWE-Dev, covering 17 chatbot LLMs, 10 reasoning models, and 10 Multi-Agent Systems (MAS), reveal that FDD is a profoundly challenging frontier for current AI (e.g., Claude-3.7-Sonnet achieves only 22.45\\% Pass@3 on the hard test split). Crucially, we demonstrate that SWE-Dev serves as an effective platform for model improvement: fine-tuning on training set enabled a 7B model comparable to GPT-4o on \\textit{hard} split, underscoring the value of its high-quality training data. Code is available here \\href{https://github.com/DorothyDUUU/SWE-Dev}{https://github.com/DorothyDUUU/SWE-Dev}.","url_abs":"https://arxiv.org/abs/2505.16975v2","url_pdf":"https://arxiv.org/pdf/2505.16975v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"swe-dev-evaluating-and-training-autonomous","repo_url":"https://github.com/dorothyduuu/swe-dev","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"bug-fixing","task_name":"Bug fixing"},{"task_slug":"chatbot","task_name":"Chatbot"},{"task_slug":"code-completion","task_name":"Code Completion"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.16975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16975"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dorothyduuu/swe-dev","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":4},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"dec11fb806839a62","entry":"get_next_metadata_index","repo":"dorothyduuu/swe-dev","repo_kind":"official","path":"infer/MAS/run_eval.py","file_url":"https://github.com/dorothyduuu/swe-dev/blob/HEAD/infer/MAS/run_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dec11fb806839a62"}},{"code_sha256_prefix":"222df7f42623404e","entry":"load_model_api_config","repo":"dorothyduuu/swe-dev","repo_kind":"official","path":"infer/MAS/run_inference.py","file_url":"https://github.com/dorothyduuu/swe-dev/blob/HEAD/infer/MAS/run_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"222df7f42623404e"}},{"code_sha256_prefix":"072ef17008be201c","entry":"parse_pytest_output","repo":"dorothyduuu/swe-dev","repo_kind":"official","path":"infer/MAS/run_eval.py","file_url":"https://github.com/dorothyduuu/swe-dev/blob/HEAD/infer/MAS/run_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"072ef17008be201c"}},{"code_sha256_prefix":"ec514b3d829fd0ba","entry":"remove_docstrings","repo":"dorothyduuu/swe-dev","repo_kind":"official","path":"infer/MAS/run_inference.py","file_url":"https://github.com/dorothyduuu/swe-dev/blob/HEAD/infer/MAS/run_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ec514b3d829fd0ba"}},{"code_sha256_prefix":"feea7b01efba05d0","entry":"reserve_unprocessed","repo":"dorothyduuu/swe-dev","repo_kind":"official","path":"infer/MAS/run_inference.py","file_url":"https://github.com/dorothyduuu/swe-dev/blob/HEAD/infer/MAS/run_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"feea7b01efba05d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}