Large Language Model-based Test Case Generation for GP Agents
Name
3638529.3654056.pdf
Size
677.51 KB
Format
Adobe PDF
Checksum (MD5)
05c29ca3f9b91d69c94755067db5704d
Author(s)
Jorgensen, Steven
Nadizar, Giorgia
Pietropolli, Gloria
Manzoni, Luca
Medvet, Eric
O'Reilly, Una-May
Hemberg, Erik
Date Issued
July 14, 2024
Publisher
ACM|Genetic and Evolutionary Computation Conference
Citation
Jorgensen, Steven, Nadizar, Giorgia, Pietropolli, Gloria, Manzoni, Luca, Medvet, Eric et al. 2024. "Large Language Model-based Test Case Generation for GP Agents."
Version
Final published version
Abstract
Genetic programming (GP) is a popular problem-solving and optimization technique. However, generating effective test cases for training and evaluating GP programs requires strong domain knowledge. Furthermore, GP programs often prematurely converge on local optima when given excessively difficult problems early in their training. Curriculum learning (CL) has been effective in addressing similar issues across different reinforcement learning (RL) domains, but it requires the manual generation of progressively difficult test cases as well as their careful scheduling. In this work, we leverage the domain knowledge and the strong generative abilities of large language models (LLMs) to generate effective test cases of increasing difficulties and schedule them according to various curricula. We show that by integrating a curriculum scheduler with LLM-generated test cases we can effectively train a GP agent player with environments-based curricula for a single-player game and opponent-based curricula for a multi-player game. Finally, we discuss the benefits and challenges of implementing this method for other problem domains.
Description
GECCO ’24, July 14–18, 2024, Melbourne, VIC, Australia
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Lincoln Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3638529.3654056
