Enhancing Knowledge Density via Hierarchical Context Pruning for Retrieval-Augmented Repository-Level Code Completion

arXiv:2508.10068 · cs.SE, cs.CL, cs.IR, cs.PL · Submitted 2025-08-13 · Read on arXiv

cs.SE, cs.CL, cs.IR, cs.PL

Submitted: 2025-08-13

Updated: 2026-10-15

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

Terminology

• Pruning — 2× in this paper · explained in 4 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes

Sources

• Program Synthesis with Large Language Models
• Evaluating Large Language Models Trained on Code
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
• CodeGen2: Lessons for Training LLMs on Programming and Natural Languages
• CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
• Code Llama: Open Foundation Models for Code
• Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties