Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; the references it cites are not checked yet.

Fully Autonomous Programming with Large Language Models

Open access
Liventsev, Vadim, Grishina, Anastasiia, Härmä, Aki, Moonen, Leon · 2023 · Proceedings of the Genetic and Evolutionary Computation Conference

Abstract

Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metrics or human evaluation), but achieve a low or even zero accuracy as measured by unit tests due to small imperfections, such as the wrong input or output format. This calls for an approach known as Synthesize, Execute, Debug (SED), whereby a draft of the solution is generated first, followed by a program repair phase addressing the failed tests. To effectively apply this approach to instruction-driven LLMs, one needs to determine which prompts perform best as instructions for LLMs, as well as strike a balance between repairing unsuccessful programs and replacing them with newly generated ones. We explore these trade-offs empirically, comparing replace-focused, repair-focused, and hybrid debug strategies, as well as different template-based and model-based prompt-generation techniques. We use OpenAI Codex as the LLM and Program Synthesis Benchmark 2 as a database of problem descriptions and tests for evaluation. The resulting framework outperforms both conventional usage of Codex without the repair phase and traditional genetic programming approaches.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3583131.3590481

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

The citation lists haven’t been fetched yet

References 53 · Cited by 45

Research works printed but not linked: 5

  1. B. Roziere , M.-A. Lachaux , G. Lample , and L. Chanussot . " Unsupervised Translation of Programming Languages." In: 34th Conference on Neural Information Processing Systems . Vancouver, Canada , 2020 . B. Roziere, M.-A. Lachaux, G. Lample, and L. Chanussot. "Unsupervised Translation of Programming Languages." In: 34th Conference on Neural Information Processing Systems. Vancouver, Canada, 2020.
  2. M. Zavershynskyi , A. Skidanov , and I. Polosukhin . NAPS: Natural Program Synthesis Dataset . 2018 . arXiv: 1807.0316. M. Zavershynskyi, A. Skidanov, and I. Polosukhin. NAPS: Natural Program Synthesis Dataset. 2018. arXiv: 1807.0316.
  3. A. Vaswani , N. Shazeer , N. Parmar , J. Uszkoreit , L. Jones , A. N. Gomez , Ł. Kaiser, and I. Polosukhin . " Attention Is All You Need." In: International Conference on Neural Information Processing Systems (NeurIPS). Ed. by I. Guyon , U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett. Curran Associates , Inc ., 2017 , pp. 5998 -- 6008 . A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. "Attention Is All You Need." In: International Conference on Neural Information Processing Systems (NeurIPS). Ed. by I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett. Curran Associates, Inc., 2017, pp. 5998--6008.
  4. 10.5555/183460 · doi:10.5555/183460
  5. B. Ahmad , S. Thakur , B. Tan , R. Karri , and H. Pearce . Fixing Hardware Security Bugs with Large Language Models. Feb. 2023 . arXiv: 2302 . 01215. B. Ahmad, S. Thakur, B. Tan, R. Karri, and H. Pearce. Fixing Hardware Security Bugs with Large Language Models. Feb. 2023. arXiv: 2302. 01215.

Metadata

Authors
Liventsev, V., Grishina, A., Härmä, A., & Moonen, L.
Affiliations
  • Philips (Netherlands) (NL)
  • University of Oslo (NO)
  • BI Norwegian Business School (NO)
Venue
Proceedings of the Genetic and Evolutionary Computation Conference
Publisher
ACM
Published
2023-07-12
Pages
1146-1155
OpenAlex
W4366735548
Cited by
45
References
53
Citations by year
2026: 5 · 2025: 17 · 2024: 19 · 2023: 4
FWCI
7.97
Type
conference paper
Language
en
Open access
Locations
  • Genetic and Evolutionary Computation Conference (GECCO) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • NORA - Norwegian Open Research Archives (submittedVersion, cc-by)
  • Research Publications (Maastricht University) (submittedVersion, other-oa)
  • arXiv (Cornell University) (cc-by)
Funders
  • Research Council of Norway (IKTPLUSS #288787)
  • The European Union?s Horizon 2020 research and innovation programme (no. 812882)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
  • Physical Sciences › Computer Science › Information Systems › Software Engineering Research
  • Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
Keywords
program synthesis, large language models, program repair, prompt engineering, prompt generation, OpenAI Codex, genetic programming comparison

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Fully Autonomous Programming with Large Language Models. https://app.cochat.ai/papers/10.1145/3583131.3590481
The paper
Liventsev, V., Grishina, A., Härmä, A., & Moonen, L. (2023). Fully Autonomous Programming with Large Language Models. Proceedings of the Genetic and Evolutionary Computation Conference. https://doi.org/10.1145/3583131.3590481

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.