홈 › Papers

ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair

2026-07-02 · Chiwang Luk, Matin Mohammad Najafi, Zhifeng Jia, Wei Yang, Xiuchang Li, Jinwei Zhu, Yang Ren, Lei Chen, Gao Cong arxiv

Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long terminal outputs where useful evidence is mixed with irrelevant code and logs. This paper presents ContextSniper, AntTrail's code-repair module for precision evidence selection in repository-level program repair, part of AntTrail's broader agent-memory engine. AntTrail is available at https://gitcode.com/datagallery/AntTrail. ContextSniper indexes code and action memory as three abstract levels, retrieves candidates with a hybrid ranker, filters long tool output through an intention-aware context gate, and returns compact evidence packets while keeping full source recoverable on demand. In a matched 50-task-per-condition comparison on SWE-bench Lite (same tasks, baseline vs.\ ContextSniper), ContextSniper reduces total token use by 51.5% and logged cost by 36.4% for OpenClaw, and by 38.9% and 27.3% for Claude Code, with submitted-resolution rates essentially unchanged in both host-agent settings. In a separate five-task comparison, ContextSniper beats existing memory- and RAG-style integrations on token efficiency. These results suggest ContextSniper can substantially cut token and cost overhead for repository-level repair agents without a measurable loss in repair quality. The evaluation harness for this study is available at https://gitcode.com/lukchiwang/ContextSniper.

📄 PDF Abstract BibTeX arXiv:2607.01916

Code (0)

등록된 구현이 없습니다.

Tasks

Program Repair

On Pretraining for Project-Level Code Completion

2025-10-15 · Maksim Sapronov, Evgeniy Glukhov arxiv

Repository-level pretraining is commonly used to enable large language models for code to leverage codebase-wide context. This enhances their ability to generate accurate and context-aware code completions. In this work,…

Code Completion

Improving Code Localization with Repository Memory

2025-10-01 · Boshi Wang, Weijian Xu, Yunsheng Li, Mei Gao 외 arxiv

Code localization is a fundamental challenge in repository-level software engineering tasks such as bug fixing. While existing methods equip language agents with comprehensive tools/interfaces to fetch information from t…

Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation

2026-02-04 · Nikita Sorokin, Ivan Sedykh, Valentin Malykh arxiv

Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long contexts. We present Hierarchical Embed…

Code Generation Code Completion

Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases

2026-06-20 · Yiwei Hou, Hao Wang, Muxi Lyu, Marius Momeu 외 arxiv

Memory safety vulnerabilities remain a significant threat even for projects with extensive fuzzing and manual auditing. Recent results suggest that large language models hold great promise for detecting such vulnerabilit…

Vulnerability Detection

Learning to Commit: Generating Organic Pull Requests via Online Repository Memory

2026-03-27 · Mo Li, L. H. Xu, Qitai Tan, Ting Cao 외 arxiv

Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a la…