Pith. sign in

REVIEW 3 cited by

CodeS: Natural Language to Code Repository via Multi-Layer Sketch

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 2403.16443 v1 pith:YLE72DIM submitted 2024-03-25 cs.CL cs.AIcs.SE

classification cs.CLcs.AIcs.SE
keywords codestasklanguagenl2reporepositorysketchcodeevaluation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a new software engineering task, namely Natural Language to code Repository (NL2Repo). This task aims to generate an entire code repository from its natural language requirements. To address this task, we propose a simple yet effective framework CodeS, which decomposes NL2Repo into multiple sub-tasks by a multi-layer sketch. Specifically, CodeS includes three modules: RepoSketcher, FileSketcher, and SketchFiller. RepoSketcher first generates a repository's directory structure for given requirements; FileSketcher then generates a file sketch for each file in the generated structure; SketchFiller finally fills in the details for each function in the generated file sketch. To rigorously assess CodeS on the NL2Repo task, we carry out evaluations through both automated benchmarking and manual feedback analysis. For benchmark-based evaluation, we craft a repository-oriented benchmark, SketchEval, and design an evaluation metric, SketchBLEU. For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies. Extensive experiments prove the effectiveness and practicality of CodeS on the NL2Repo task.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models

    cs.SE 2025-09 conditional novelty 6.0 of 10

    RepoDebug is a new multi-language, multi-task benchmark for repository-level code debugging on which current LLMs, including the best model Claude 3.5 Sonnet, perform poorly.

  2. Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details

    cs.AI 2026-08 conditional novelty 5.0 of 10

    For Other-Play in Yokai, agents trained with different implementation details coordinate across implementations about as well as across seeds, supporting inter-seed cross-play as a proxy for cross-implementation evaluation.

  3. Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews

    cs.AI 2025-02 conditional novelty 4.0 of 10

    A CrewAI-based multi-agent system with human oversight built financial models and carried out model risk management checks on three public credit datasets, with results comparable to AutoML and Kaggle baselines.

Pith tools