arXiv cs.AI· Xiaocong Yang, Rishit Chatterjee, Himanshu Udupi, Vikram Ramavarapu, ChengXiang Zhai·· 3 小时前AI 评分55
CQ2-CARE 论文显示编码智能体按整文件选上下文比压缩和检索修复更多问题
Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files
AI 导读
arXiv 论文提出 CQ2-CARE 文件选择器，在 300 个 SWE-rebench 问题上按相同 token 预算对比整文件选择、压缩与检索。使用 GPT-5.6 和 Claude Opus 5 时分别解决 43.7% 和 46.7% 的问题，比最佳压缩器高 6.3 分，比最佳检索器高 9.3 和 12.7 分。分析显示检索常漏掉待改文件，压缩虽保留文件却改变代码文本导致补丁更难套用。
正文 · 原文
Abstract:A coding agent works on repositories that can be far larger than its context window can hold. Prompt compressors and retrievers offer solutions to this problem, but patching an issue needs two things at once: the files that must change, and their code exactly as written, since the model must reproduce the lines it edits. Retrievers rank code by its similarity to the issue rather than by whether it must change, and compressors delete text to fit the budget. We show that at an equal token budget, an agent resolves more issues when the budget goes to choosing which files to show verbatim, as our simple selector CQ2-CARE does, than when it goes to pruning tokens or retrieving chunks. We fit every context to the same per-issue budget on 300 recent SWE-rebench issues and grade each patch with the benchmark's tests. With GPT-5.6 and Claude Opus 5, CQ2-CARE resolves 43.7% and 46.7% of the issues, 6.3 points more than the best of three compressors with either model, and 9.3 and 12.7 points more than the best of three retrievers. CQ2-CARE even resolves more issues than two methods trained for issue resolution, SweRank (by 0.7 and 1.7 points) and SWE-Pruner (by 2.0 and 7.3). Our analysis shows the defects of the baseline methods: retrievers often miss the files to edit, and compressors keep them but alter their text, so fewer patches apply. Exact-file selection needs no compression model and shows every line as the repository has it, so the model can quote the code it edits.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.21073 [cs.SE] |
| (or arXiv:2610.21073v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21073 arXiv-issued DOI via DataCite |
Submission history
From: Vikram Ramavarapu [view email]
[v1]
Thu, 15 Oct 2026 01:21:36 UTC (900 KB)
来源：arXiv cs.AI · arxiv.org