Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

arXiv:2609.01601 · cs.SE, cs.AI, cs.CL · Submitted 2026-09-01 · Read on arXiv

cs.SE, cs.AI, cs.CL

Submitted: 2026-09-01

Updated: 2026-09-01

Code: https://github.com/DeepSoftwareAnalytics/ACToR

Terminology

• Benchmark — 25× in this paper · explained in 2 episodes
• Core — 13× in this paper · explained in 2 episodes
• RAG — 8× in this paper · explained in 3 episodes
• Hallucination — 6× in this paper · explained in 4 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Benchmarking — 4× in this paper · explained in 4 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• KV cache — 4× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Automated Software Engineering — 3× in this paper
• International Conference on Software Engineering — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Actor — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptive Mechanism — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• Evaluating Large Language Models Trained on Code
• RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing
• Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion
• Repoformer: Selective Retrieval for Repository-Level Code Completion
• R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• Code Llama: Open Foundation Models for Code
• Let the Code LLM Edit Itself When You Edit the Code
• A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends
• Towards an Understanding of Context Utilization in Code Intelligence
• CodeT: Code Generation with Generated Tests
• ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation
• CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
• StarCoder: may the source be with you!
• StarCoder 2 and The Stack v2: The Next Generation
• InCoder: A Generative Model for Code Infilling and Synthesis
• PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
• SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
• SWE-Prime: Fewer Trajectories, Better Performance
• From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench

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