Published September 12, 2024 | Version v1
Software Open

Replication package for "Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models"

  • 1. ROR icon Simula Research Laboratory
  • 2. ROR icon University of Oslo
  • 3. ROR icon Eindhoven University of Technology
  • 4. ROR icon Philips (Netherlands)

Description

This repository contains the replication package for the paper Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models, Anastasiia Grishina, Vadim Liventsev, Aki Härmä, and Leon Moonen, under review for ACM Transactions on Evolutionary Learning and Optimization.

The replication package is archived on Zenodo with DOI: 10.5281/zenodo.13754705. The source code is distributed under the MIT license, the data is distributed under the CC BY 4.0 license.

Organization

The repository is organized as follows:

  • Archived source code in the src folder, with a dedicated README.

  • Analysis of the results in the analysis folder, with a dedicated README.

  • Archive of SEIDR-generated solutions as a git bundle: seidr-solutions.bundle.

    • These solutions can be inspected by cloning the bundle using git clone seidr-solutions.bundle which will create a folder seidr-solutions with a dedicated README in the master branch.
    • The other branches contain the code that was generated in specific experiments/configurations. List which experiments are available using git branch -r, select one using git checkout <branch>, and look at the iteratively synthesized solution for a problem using git log -p -- {problem}.{cpp/py}. Alternatively, these can be inspected on GitHub.

Citation

If you build on this data or code, please cite this work by referring to the paper:

@article{grishina2025:fully,
   title = {Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models},
   author = {Anastasiia Grishina and Vadim Liventsev and Aki Härmä and Leon Moonen},
   journal = {Transactions on Evolutionary Learning and Optimization},
   year = {2025},
   publisher = {ACM}
   note = {Under review}
}

External References

Notes

Acknowledgement

The work included in this repository was supported by the European Union through Horizon 2020 grant 812882, and by the Research Council of Norway through the secureIT project (#288787). The empirical evaluation made use of the Experimental Infrastructure for Exploration of Exascale Computing (eX3), financially supported by the Research Council of Norway through project #270053.

Files

SEIDR-TELO.zip

Files (507.9 MB)

Name Size Download all
md5:49054bf6fcc84dcda08f5fa77a94f0e3
507.9 MB Preview Download

Additional details

Funding

European Commission
PhilHumans - Personal Health Interfaces Leveraging Human-Machine Natural Interactions 812882
The Research Council of Norway
secureIT 288787
The Research Council of Norway
Experimental Infrastructure for Exploration of Exascale Computing (eX3) 270053