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.
- SwarmRSI evolves scientific agent swarms through recursive self-improvement.
- Feedback-guided mutation revises hypotheses and implementations.
- Recombination reuses hypotheses and complementary program components.
- Authors report SOTA on OpenProblems, NatureBench, and MLE-Bench Lite.
- Accumulated experience improved performance on held-out tasks.
Full article169 words · extracted from huggingface.co · click to collapse
Recursive self-improvement (RSI) in scientific research aims to improve agents' research capabilities through their own experimental experience. Scientific agent swarms can combine evidence and implementations from different research directions to guide their agents' subsequent experiments. However, poor experimental results can leave unclear whether to revise a hypothesis or its implementation, while overall program scores can hide components useful to other agents. To address these challenges, we introduce SwarmRSI, a framework that evolves scientific agent swarms for recursive self-improvement. We devise Feedback-Guided Swarm Mutation to refine hypotheses and their implementations using experimental feedback from other agents. We also propose Complementary Swarm Recombination to reuse retained hypotheses and complementary program components across agents, allowing partial results to support new research. Recursive Swarm Evolution integrates both mechanisms into a feedback loop, using new experimental evidence to guide subsequent research. Experiments on OpenProblems, NatureBench and MLE-Bench Lite demonstrate SwarmRSI's state-of-the-art (SOTA) performance. Further evaluations show that accumulated research experience improves performance on held-out tasks. Biologists also reproduce its programs for follow-up biological analyses.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2610.20431