{"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/thinking-longer-not-larger-enhancing-software","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","arxiv_id":"2503.23803","date":"2025-03-31","proceeding":null,"authors":["Yingwei Ma","Yongbin Li","Yihong Dong","Xue Jiang","Rongyu Cao","Jue Chen","Fei Huang","Binhua Li"],"abstract":"Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource-intensive models introduces significant deployment challenges in private environments, prompting a critical question: \\textit{How can personally deployable open-source LLMs achieve comparable code reasoning performance?} To this end, we propose a unified Test-Time Compute scaling framework that leverages increased inference-time computation instead of larger models. Our framework incorporates two complementary strategies: internal TTC and external TTC. Internally, we introduce a \\textit{development-contextualized trajectory synthesis} method leveraging real-world software repositories to bootstrap multi-stage reasoning processes, such as fault localization and patch generation. We further enhance trajectory quality through rejection sampling, rigorously evaluating trajectories along accuracy and complexity. Externally, we propose a novel \\textit{development-process-based search} strategy guided by reward models and execution verification. This approach enables targeted computational allocation at critical development decision points, overcoming limitations of existing \"end-point only\" verification methods. Evaluations on SWE-bench Verified demonstrate our \\textbf{32B model achieves a 46\\% issue resolution rate}, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1. Additionally, we provide the empirical validation of the test-time scaling phenomenon within SWE agents, revealing that \\textbf{models dynamically allocate more tokens to increasingly challenging problems}, effectively enhancing reasoning capabilities. We publicly release all training data, models, and code to facilitate future research. https://github.com/yingweima2022/SWE-Reasoner","url_abs":"https://arxiv.org/abs/2503.23803v2","url_pdf":"https://arxiv.org/pdf/2503.23803v2.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":"thinking-longer-not-larger-enhancing-software","repo_url":"https://github.com/yingweima2022/swe-reasoner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fault-localization","task_name":"Fault localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.23803","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}