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

arXiv:2607.01916 · cs.AI · Submitted 2026-07-02 · Read on arXiv

cs.AI

Submitted: 2026-07-02

Updated: 2026-09-14

Code: https://github.com/Calluking/ContextSniper

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 10× in this paper · explained in 2 episodes
• RAG — 10× in this paper · explained in 3 episodes
• Trace — 7× in this paper · explained in 2 episodes
• AI Agents — 4× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Knowledge Graph — 4× in this paper · explained in 7 episodes
• Provenance — 4× in this paper · explained in 3 episodes
• Agent Memory — 3× in this paper · explained in 1 episode
• Knowledge graphs — 3× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action Views — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Grounding — 1× in this paper · explained in 3 episodes

Sources

• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• AutoCodeRover: Autonomous Program Improvement
• Agentless: Demystifying LLM-based Software Engineering Agents
• ACON: Optimizing Context Compression for Long-horizon LLM Agents
• Lost in the Middle: How Language Models Use Long Contexts
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
• Enhancing repository-level software repair via repository-aware knowledge graphs
• Improving Code Localization with Repository Memory
• SWE-Exp: Experience-Driven Software Issue Resolution
• EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair
• MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
• Structurally Aligned Subtask-Level Memory for Software Engineering Agents
• Learning from Execution: Self-Evolving Memory for Private-Library Code Generation
• Learning to Commit: Generating Organic Pull Requests via Online Repository Memory
• LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
• GVGEN: Text-to-3D Generation with Volumetric Representation
• RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection