Pith. sign in

REVIEW 21 cited by

RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation

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 2303.12570 v3 pith:GXOOCQOX submitted 2023-03-22 cs.CL cs.AIcs.PLcs.SE

Fengji Zhang , Bei Chen , Yue Zhang , Jacky Keung , Jin Liu , Daoguang Zan , Yi Mao , Jian-Guang Lou
show 1 more author
Weizhu Chen
This is my paper · ORCID
classification cs.CLcs.AIcs.PLcs.SE
keywords codecompletionrepocoderrepository-levelbenchmarkeffectiveinformationiterative
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository. While for automated code completion tools, it is difficult to utilize the useful information scattered in different files. We propose RepoCoder, a simple, generic, and effective framework to address the challenge. It streamlines the repository-level code completion process by incorporating a similarity-based retriever and a pre-trained code language model in an iterative retrieval-generation pipeline. RepoCoder makes effective utilization of repository-level information for code completion and has the ability to generate code at various levels of granularity. Moreover, we propose a new benchmark RepoEval, which consists of the latest and high-quality real-world repositories covering line, API invocation, and function body completion scenarios. Experimental results indicate that RepoCoder significantly improves the In-File completion baseline by over 10% in all settings and consistently outperforms the vanilla retrieval-augmented code completion approach. Furthermore, we validate the effectiveness of RepoCoder through comprehensive analysis, providing valuable insights for future research. Our source code and benchmark are publicly available: https://github.com/microsoft/CodeT/tree/main/RepoCoder

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 21 Pith papers

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

  1. SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner

    cs.CL 2025-06 conditional novelty 7.0 of 10

    SWE-Flow synthesizes incremental, test-driven development tasks from real GitHub projects and shows that fine-tuning Qwen2.5-Coder-32B-Instruct on them improves performance on the resulting SWE-Flow-Bench benchmark.

  2. Knowledge-Guided Synthetic Bug Feedback for LLM-Based Unit Test Generation

    cs.SE 2026-07 conditional novelty 6.5 of 10

    Mechanism-guided synthetic-bug feedback raises real-bug detection of LLM unit tests to 72.67% RBDR on 172 Defects4J tasks, outperforming mutation and coverage baselines by ~20 points.

  3. 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.

  4. Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization

    cs.CR 2026-03 conditional novelty 6.0 of 10

    Knowdit links abstract DeFi semantics to vulnerability patterns in a knowledge graph and drives an agentic specify–harness–fuzz–reflect loop that finds all high-severity and most medium-severity bugs on held-out Code4...

  5. 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.

  6. MRG-Bench: Evaluating and Exploring the Requirements of Context for Repository-Level Code Generation

    cs.SE 2025-08 conditional novelty 6.0 of 10

    MRG-Bench is a multi-language, executable repository-level code generation benchmark on which current LLMs and RAG methods perform poorly, with the dominant failure mode being poor understanding of user requirements.

  7. CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors

    cs.CL 2025-08 conditional novelty 6.0 of 10

    MRG-Bench is a multi-language, runnable-test benchmark showing that LLMs' main failure in repository-level code generation is understanding user requirements.

  8. IFEvalCode: Controlled Code Generation

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A 1,620-sample, 8-language, Chinese/English benchmark separates code correctness from instruction-following and shows instruction compliance is far lower than correctness across 40+ LLMs.

  9. 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.

  10. Seed-Coder: Let the Code Model Curate Data for Itself

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Seed-Coder shows that an LLM-trained quality scorer can filter 6T tokens of code data and yield 8B models that outperform similar-size open code models.

  11. RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

    cs.SE 2025-05 conditional novelty 6.0 of 10

    RepoMaster, a repository-aware code agent, lifts the task pass rate from 40.7% to 62.9% and cuts token use by about 95% versus OpenHands on the new GitTaskBench benchmark.

  12. Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks

    cs.SE 2025-05 conditional novelty 6.0 of 10

    A graph-integrated open-source LLM with agentless RAG resolves 43% of SWE-bench Lite issues, best among open-weight models.

  13. Knowledge-Enhanced Program Repair for Data Science Code

    cs.SE 2025-02 conditional novelty 6.0 of 10

    DSrepair combines a knowledge graph of data science APIs with AST-level bug localization to repair LLM-generated code, fixing more DS-1000 tasks than five baseline repair methods.

  14. Repository-level Code Search with Neural Retrieval Methods

    cs.IR 2025-02 conditional novelty 6.0 of 10

    A commit-history-aware retrieval pipeline combining BM25 with CodeBERT rerankers substantially improves file-level code search on a self-created seven-repository benchmark.

  15. Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Across 10 LLMs and 5 prompting strategies, curated context yields the best syntactic quality, yet simulation fidelity stays near zero for nearly all configurations.

  16. 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.

  17. ChatVis: Large Language Model Agent for Generating Scientific Visualizations

    cs.HC 2025-07 conditional novelty 5.0 of 10

    A retrieval-augmented LLM assistant with iterative error correction nearly doubles the rate of generating executable ParaView visualization scripts compared with unassisted models.

  18. SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization

    cs.CL 2025-06 reject novelty 5.0 of 10

    Code retrievers rely on surface text like identifiers and docstrings rather than code semantics, and a description-based reranking pipeline, SACL, compensates for that bias but its headline gains come mostly from arti...

  19. Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A survey that classifies AI agent evaluation benchmarks along environment and capability axes, and proposes five traits that distinguish agents from chatbots.

  20. Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning

    cs.SE 2025-06 conditional novelty 4.0 of 10

    Repairity lifts Qwen2.5-Coder-32B from 38.2% to 62.7% on SWE-bench Verified by distilling Claude's reasoning traces and then fine-tuning with a reward model trained on Claude preferences.

  21. Knowledge Graph Based Repository-Level Code Generation

    cs.AI 2025-05 reject novelty 4.0 of 10

    A knowledge graph code retrieval pipeline is described, but its headline results come from an evaluation that skips the retrieval step and anchors context on the known target function.

Pith tools