Pith. sign in

REVIEW 30 cited by

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

Not yet reviewed by Pith; the record is open.

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

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

classification cs.CL cs.AIcs.PLcs.SE
keywords codecompletionrepocoderrepository-levelbenchmarkeffectiveinformationiterative
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
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)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 30 Pith papers

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

  1. An Empirical Study of LLM-Generated Specifications for VeriFast

    cs.SE 2026-06 unverdicted novelty 7.0

    LLMs preserve functional behavior in over 91% of generated VeriFast specifications and source code but achieve only 31.4% verification success, with 94% of failures due to separation logic domain knowledge errors.

  2. RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations

    cs.SE 2026-05 unverdicted novelty 7.0

    RepoMirage uses semantics-preserving perturbations on SWE-Bench to show code agents lack repository context reasoning, with performance falling sharply on extended structure tasks, and introduces RepoAnchor as a struc...

  3. Constrained Code Generation with Discrete Diffusion

    cs.CL 2026-05 unverdicted novelty 7.0

    Constrained Diffusion for Code (CDC) integrates constraint satisfaction into the reverse denoising process of discrete diffusion models via constraint-aware operators that use optimization and program analysis to stee...

  4. When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context

    cs.SE 2026-05 accept novelty 7.0

    Stale repository context in code RAG actively induces models to produce obsolete helper references, raising stale outputs by 76-88 percentage points over current-only retrieval in a 17-sample diagnostic study.

  5. ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation

    cs.SE 2026-04 unverdicted novelty 7.0

    ClassEval-Pro benchmark shows frontier LLMs achieve at most 45.6% Pass@1 on class-level code tasks, with logic errors (56%) and dependency errors (38%) as dominant failure modes.

  6. RepoDoc: A Knowledge Graph-Based Framework to Automatic Documentation Generation and Incremental Updates

    cs.SE 2026-04 unverdicted novelty 7.0

    RepoDoc uses a repository knowledge graph with module clustering and semantic impact propagation to generate more complete documentation 3x faster with 85% fewer tokens and handle incremental updates 73% faster than p...

  7. PerfCoder: Large Language Models for Interpretable Code Performance Optimization

    cs.SE 2025-12 unverdicted novelty 7.0

    PerfCoder is a family of LLMs trained on optimization trajectories with human annotations and runtime-based preference alignment that achieves higher runtime speedups and optimization rates on the PIE benchmark than p...

  8. Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software

    cs.SE 2025-10 unverdicted novelty 7.0

    LLMs propose volatile performance improvements on real-world Java tasks that lag human developers on average, showing algorithmic benchmarks overestimate capabilities.

  9. From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems

    cs.MA 2025-06 accept novelty 7.0

    A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.

  10. FastContext: Training Efficient Repository Explorer for Coding Agents

    cs.SE 2026-06 unverdicted novelty 6.0

    FastContext adds a dedicated repository-exploration subagent powered by bootstrapped 4B-30B models that improves coding-agent resolution by up to 5.5% and cuts token use by up to 60% on SWE-bench Multilingual, Pro, an...

  11. Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 6.0

    CodeThinker improves LLM code reasoning via consistency-based RL with stepwise training data, dynamic beam sampling, and consistency rewards, reaching SOTA on benchmarks with 4.3% gains on Qwen2.5-Coder-7B.

  12. Contextualized Code Pretraining for Code Generation

    cs.SE 2026-05 unverdicted novelty 6.0

    Introduces contextualized code pretraining with caller-callee pairs from static analysis to train CallerGen models that outperform baselines on the new CallerEval benchmark.

  13. XSearch: Explainable Code Search via Concept-to-Code Alignment

    cs.SE 2026-05 unverdicted novelty 6.0

    XSearch achieves explainable code search by breaking queries into functional concepts and matching them directly to code statements, delivering large gains on out-of-distribution benchmarks.

  14. XSearch: Explainable Code Search via Concept-to-Code Alignment

    cs.SE 2026-05 unverdicted novelty 6.0

    XSearch achieves 15x gains on out-of-distribution code search benchmarks by replacing global embedding similarity with explicit concept-to-statement alignment.

  15. SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    SkillLens organizes skills into policies-strategies-procedures-primitives layers, retrieves via degree-corrected random walk, and uses a verifier for local adaptation, yielding up to 6.31 pp gains on MuLocbench and ra...

  16. PaT: Planning-after-Trial for Efficient Test-Time Code Generation

    cs.CL 2026-05 unverdicted novelty 6.0

    PaT defers planning until after failed trials in LLM code generation, enabling heterogeneous cheap-plus-powerful model setups that match large-model performance at roughly 69% lower cost.

  17. RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices

    cs.SE 2026-04 unverdicted novelty 6.0

    RealBench is a new repo-level code generation benchmark that adds UML diagrams to natural language specs, showing LLMs struggle more at full repositories, create modules with errors, and perform best with whole-repo g...

  18. A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks

    cs.CV 2025-12 unverdicted novelty 6.0

    NN-RAG extracts 1,289 candidate neural modules from 19 PyTorch repositories, validates 941 of them, and supplies roughly 72% of the novel structures in the LEMUR dataset while enabling cross-repository migration.

  19. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

    cs.SE 2024-03 unverdicted novelty 6.0

    LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.

  20. How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring

    cs.SE 2026-06 unverdicted novelty 5.0

    An empirical study finds that injecting call/inheritance topology as comments improves LLM code agent localization by 2.2pp, shortens trajectories by 1.6 rounds, and halves run-to-run variance on medium repositories v...

  21. How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring

    cs.SE 2026-06 conditional novelty 5.0

    Lightweight call and inheritance topology injected as comments improves function localization by 2.2pp, shortens trajectories, and halves run-to-run variance in LLM code agents, with benefits depending on repository scale.

  22. FastContext: Training Efficient Repository Explorer for Coding Agents

    cs.SE 2026-06 unverdicted novelty 5.0

    FastContext adds a dedicated exploration subagent with specialized models trained on reference trajectories and task rewards, cutting token consumption up to 60% and lifting resolution rates up to 5.5% on SWE-bench variants.

  23. I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications

    cs.CL 2026-05 unverdicted novelty 5.0

    A Paper-to-Interactive-System Agent and I-WebGenBench benchmark with 19 papers enable converting scientific PDFs into executable interactive web systems, with PaperVoyager framework shown to improve quality.

  24. How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study

    cs.SE 2026-05 conditional novelty 5.0

    Function-based chunking underperforms other strategies in RAG code completion by 3.57-5.64 points, with context length as the dominant factor.

  25. RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices

    cs.SE 2026-04 conditional novelty 5.0

    RealBench is a repo-level code generation benchmark pairing UML diagrams with natural language requirements, revealing that LLMs perform significantly worse on realistic repo-level tasks than existing benchmarks suggest.

  26. Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent

    cs.AI 2026-06 unverdicted novelty 4.0

    Ablation study finds that a structural codebase index improves localization and resolve rates in coding agents on two SWE benchmarks without raising per-cell cost.

  27. Short-Term Gain, Long-Term Fragility: AI Labor Substitution and the Erosion of Sustainable Capability

    cs.CY 2026-04 conditional novelty 4.0

    AI labor substitution creates short-term efficiency by masking the erosion of human capability, apprenticeship pipelines, and institutional memory, producing long-term fragility.

  28. An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models

    cs.SE 2026-04 unverdicted novelty 4.0

    Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.

  29. Qwen2.5-Coder Technical Report

    cs.CL 2024-09 unverdicted novelty 4.0

    Qwen2.5-Coder models claim state-of-the-art results on over 10 code benchmarks, outperforming larger models of similar size.

  30. A Comprehensive Overview of Large Language Models

    cs.CL 2023-07 unverdicted novelty 2.0

    A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.