Large Language Models (LLMs) are now capable of resolving real-world GitHub issues. However, current approaches overapproximate the code context and suffer from two compounding problems: the prohibitive cost of processing massive inputs, and low effectiveness as noise floods the context window and distracts the model from the bug-fixing signal. Existing compression techniques fail to resolve this tension: generic compressors compromise the semantic integrity of code, while code-specific tools lack awareness of code structure and task context to preserve essential patch ingredients. To address this, we propose a novel framework consisting of two components. First, Oracle-guided Code Distillation (OCD), a context distillation algorithm that combines genetic search and delta debugging to systematically reduce code contexts to their minimal sufficient subsequence - retaining only the ingredients required for a successful fix. We use this distilled data to fine-tune SWEzze, a lightweight model that learns to compress code context at inference time, filtering noise and combating distraction while preserving fix ingredients. Evaluated on SWE-bench Verified across three frontier LLMs, SWEzze maintains a stable compression rate of about 6 times across models, reduces the total token budget by 51.8%-71.3% relative to the uncompressed setting, improves issue resolution rates by 5.0%-9.2%, and delivers the best overall balance among effectiveness, compression ratio, and latency compared with state-of-the-art context compression baselines.
What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues
Drexel University(德雷塞尔大学);Belmont University(贝尔蒙特大学);Florida State University(佛罗里达州立大学)
REAgent: Requirement-Driven LLM Agents for Software Issue Resolution
School of Computer Software, Tianjin University(天津大学计算机软件学院);The International Joint Institute of Tianjin University, Tianjin University(天津大学国际联合学院);HUAWEI Technologies(华为技术有限公司)
Agentic Software Issue Resolution with Large Language Models: A Survey
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学);School of Computing and Information Systems, Singapore Management University(计算与信息系统学院,新加坡管理大学)
Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents
Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology(南方科技大学可信自主系统研究院);Southern University of Science and Technology(南方科技大学);Ant Group(蚂蚁集团)
Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey
Sun Yat-sen University(中山大学);Hangzhou Normal University(杭州师范大学);Zhejiang University(浙江大学);Huawei Technologies Co, Ltd(华为技术有限公司);Chongqing University(重庆大学)
Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全国家重点实验室);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术开发区(滨江)区块链与数据安全研究院);Graz University of Technology(格拉茨工业大学)
该研究以SWE-bench等基准的F2P测试为工具,搭配Claude Opus 5等模型与SWE-agent,发现LLM生成补丁的运行时性能与问题解决率无关,需将补丁性能纳入仓库级问题解决的评估。
IBM;Institute for Clarity in Documentation(文献清晰研究所);Inria Paris-Rocquencourt(法国国家信息与自动化研究所巴黎-罗康库尔);Rajiv Gandhi University(拉吉夫·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕默研究实验室)