InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911277292453888 |
|---|---|
| author | Li, KeFan Wang, Mengfei Zhang, Hengzhi Li, Zhichao Yuan, Yuan Li, Mu Gao, Xiang Sun, Hailong Hu, Chunming Lv, Weifeng |
| author_facet | Li, KeFan Wang, Mengfei Zhang, Hengzhi Li, Zhichao Yuan, Yuan Li, Mu Gao, Xiang Sun, Hailong Hu, Chunming Lv, Weifeng |
| contents | Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing agent-based and pipeline-based methods often rely on insufficient tests, which can lead to patches that satisfy verification but fail to fix the underlying defect. We present InfCode, an adversarial multi-agent framework for automated repository-level issue resolution. InfCode iteratively refines both tests and patches through adversarial interaction between a Test Patch Generator and a Code Patch Generator, while a Selector agent identifies the most reliable fix. The framework runs inside a containerized environment that supports realistic repository inspection, modification, and validation. Experiments on SWE-bench Lite and SWE-bench Verified using models such as DeepSeek-V3 and Claude 4.5 Sonnet show that InfCode consistently outperforms strong baselines. It achieves 79.4% performance on SWE-bench Verified, establishing a new state-of-the-art. We have released InfCode as an open-source project at https://github.com/Tokfinity/InfCode. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16004 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution Li, KeFan Wang, Mengfei Zhang, Hengzhi Li, Zhichao Yuan, Yuan Li, Mu Gao, Xiang Sun, Hailong Hu, Chunming Lv, Weifeng Software Engineering Artificial Intelligence Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing agent-based and pipeline-based methods often rely on insufficient tests, which can lead to patches that satisfy verification but fail to fix the underlying defect. We present InfCode, an adversarial multi-agent framework for automated repository-level issue resolution. InfCode iteratively refines both tests and patches through adversarial interaction between a Test Patch Generator and a Code Patch Generator, while a Selector agent identifies the most reliable fix. The framework runs inside a containerized environment that supports realistic repository inspection, modification, and validation. Experiments on SWE-bench Lite and SWE-bench Verified using models such as DeepSeek-V3 and Claude 4.5 Sonnet show that InfCode consistently outperforms strong baselines. It achieves 79.4% performance on SWE-bench Verified, establishing a new state-of-the-art. We have released InfCode as an open-source project at https://github.com/Tokfinity/InfCode. |
| title | InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2511.16004 |