Pith. sign in

REVIEW 10 cited by

RLCoder: Reinforcement Learning for Repository-Level Code Completion

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.19487 v1 pith:ZFITADSJ submitted 2024-07-28 cs.SE

Yanlin Wang , Yanli Wang , Daya Guo , Jiachi Chen , Ruikai Zhang , Yuchi Ma , Zibin Zheng This is my paper
classification cs.SE
keywords codemethodscontentretrieverrlcodercompletioncontextdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Repository-level code completion aims to generate code for unfinished code snippets within the context of a specified repository. Existing approaches mainly rely on retrieval-augmented generation strategies due to limitations in input sequence length. However, traditional lexical-based retrieval methods like BM25 struggle to capture code semantics, while model-based retrieval methods face challenges due to the lack of labeled data for training. Therefore, we propose RLCoder, a novel reinforcement learning framework, which can enable the retriever to learn to retrieve useful content for code completion without the need for labeled data. Specifically, we iteratively evaluate the usefulness of retrieved content based on the perplexity of the target code when provided with the retrieved content as additional context, and provide feedback to update the retriever parameters. This iterative process enables the retriever to learn from its successes and failures, gradually improving its ability to retrieve relevant and high-quality content. Considering that not all situations require information beyond code files and not all retrieved context is helpful for generation, we also introduce a stop signal mechanism, allowing the retriever to decide when to retrieve and which candidates to retain autonomously. Extensive experimental results demonstrate that RLCoder consistently outperforms state-of-the-art methods on CrossCodeEval and RepoEval, achieving 12.2% EM improvement over previous methods. Moreover, experiments show that our framework can generalize across different programming languages and further improve previous methods like RepoCoder. We provide the code and data at https://github.com/DeepSoftwareAnalytics/RLCoder.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models

    cs.SE 2026-07 conditional novelty 7.0 of 10

    RepoReasoner is a repository-level code-reasoning benchmark with output-prediction and call-chain tasks; the best LLM reaches only 69.1% Pass@1 even with oracle context, with low recall in dependency tracing.

  2. PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A multi-agent repair framework that samples multiple edit locations and iteratively reflects on patch attempts reaches 76.0% Pass@1 on SWE-bench-Verified, up to a 7.8% relative gain over SWE-agent.

  3. Better Call Grep: Evaluating and Improving Grep-Like Lexical Retrieval for Repository-Level Code Completion

    cs.SE 2026-01 conditional novelty 6.0 of 10

    LLM-generated ripgrep queries plus BM25 re-ranking and line-interval de-duplication outperform graph- and RL-based retrievers for repository-level code completion on CrossCodeEval and RepoEval-Updated.

  4. Enhancing Project-Specific Code Completion by Inferring Internal API Information

    cs.SE 2025-07 conditional novelty 6.0 of 10

    A retrieval-augmented code completion method that infers project-internal APIs from a rough draft and a static knowledge base, beating existing repo-level baselines.

  5. CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning

    cs.SE 2025-07 conditional novelty 6.0 of 10

    CodeReasoner combines a concise execution-focused dataset, instruction tuning, and GRPO RL to make 7B/14B models match or beat GPT-4o on code reasoning benchmarks.

  6. Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation

    cs.SE 2026-07 conditional novelty 5.0 of 10

    Uncertainty-aware multi-source retrieval improves GPT repository-level code selection over plain RAG but matches verification-and-repair alone and is backend- and context-dependent.

  7. GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion

    cs.SE 2025-09 conditional novelty 5.0 of 10

    GRACE combines a multi-level code graph, hybrid text-structure retrieval, and graph fusion to improve repository-level code completion over vanilla and graph-based RAG baselines.

  8. A Survey of Reinforcement Learning for Software Engineering

    cs.SE 2025-07 conditional novelty 5.0 of 10

    A systematic survey of 115 reinforcement learning for software engineering papers finds most activity in quality assurance and test generation, with sparse coverage of requirements, management, and advanced RL algorithms.

  9. Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection

    cs.CR 2025-06 conditional novelty 5.0 of 10

    A LLaMA-3.1-8B model trained with continual pre-training, supervised fine-tuning, and direct preference optimization reports state-of-the-art accuracy and F1 for smart contract vulnerability detection and explanation.

  10. Toward Rich Video Human-Motion2D Generation

    cs.CV 2025-06 reject novelty 4.0 of 10

    A new 150K-video 2D skeleton dataset with text captions and a diffusion model for single- and double-character motion generation, though the claimed FID-rewarded RL training is misrepresented.

Pith tools