SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm
SwarmRSI reports state-of-the-art recursive self-improvement for scientific agent swarms on three research benchmarks.
SwarmRSI is a framework for recursive self-improvement of scientific agent swarms. Feedback-Guided Swarm Mutation uses other agents' experimental feedback to revise hypotheses and implementations, while Complementary Swarm Recombination reuses retained hypotheses and program components. Recursive Swarm Evolution closes the loop with new evidence. The authors report state-of-the-art results on OpenProblems, NatureBench, and MLE-Bench Lite, plus gains on held-out tasks from accumulated experience.
52