ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

2026-09-15

AI Summary

该研究通过引入ScienceBuddy平台，利用递归自改进机制结合模型强化学习，帮助科研人员在日常工作中持续优化科学任务执行，促进科学AI与研究人员的协作。

Abstract

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying out scientific tasks while transforming their requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. At its core is recursive-in-recursive self-improvement, a paradigm that couples harness evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, while the outer recursion trains the model under the improved harness. Harness evolution shapes training experience, and model learning creates new opportunities for harness adaptation. We present case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scientific task families. By releasing ScienceBuddy as a research product, we make this paradigm available to the scientific community and take a step toward discovery intelligence: scientific AI that advances through sustained collaboration with researchers and evolves alongside the research it supports. Website: http://science-buddy.io

Problem

• interactive scientific agents
• continual learning
• recursive self-improvement
• research workflow

Innovation

• recursive-in-recursive self-improvement
• model reinforcement learning
• harness evolution