Qile Jiang and George Em Karniadakis
Division of Applied Mathematics, Brown University
Step-by-step video with captions (43 s)
SwarmEvolve is a super fast, low-cost, and capable framework for LLM-guided evolutionary search. It solves problems in mathematical discovery and scientific computing by refining and recombining existing programs.
SwarmEvolve uses swarms of open-weight LLM agents, hundreds of them per round, to reason in latent space. Each swarm studies the problem with a different focus and passes their KV caches to a summarizer agent that writes a new program, so the ideas of different agents combine directly in latent space.
Qwen3 8B, one GPU, 60 minutes per run.
We compare SwarmEvolve with three open-source frameworks:
- OpenEvolve: A. Sharma, OpenEvolve: an open-source evolutionary coding agent, 2025.
- ShinkaEvolve: R. T. Lange, Y. Imajuku, and E. Cetin, ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution, International Conference on Learning Representations, 2026.
- CodeEvolve: H. Assumpção, D. Ferreira, L. Campos, and F. Murai, CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization, arXiv:2510.14150, 2025.
On 21 problems from mathematical discovery and scientific computing, with Qwen3 8B, 14B, and 32B on one GPU for 60 minutes per run, SwarmEvolve achieves the highest average score with every model.
Best score within 60 minutes, averaged over three runs. Bold: best; underline: second best.
benchmarks/problems/: the 21 problems, each withtask.md,initial_program.py, andevaluator.py.benchmarks/evaluation.py: the shared evaluation used to score every framework.benchmarks/calibration/: expert reference solvers for the scientific-computing problems.baselines/: OpenEvolve, ShinkaEvolve, and CodeEvolve at the commits used in the paper, with the scripts to run them on the benchmarks (setup_baselines.sh, thenrun_baseline.sh <framework> <problem> <model>).
The SwarmEvolve code will be released soon. For questions or early access, please reach out to the authors.