ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
ScienceBuddy couples harness evolution with model reinforcement learning so scientific agents continually self-improve from researcher feedback in an interactive workspace.
The authors release ScienceBuddy, an interactive scientific research workspace that transforms researcher requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. Its recursive-in-recursive self-improvement paradigm couples harness evolution (inner recursion, model fixed) with model reinforcement learning under the improved harness (outer recursion). Case studies span four scientific task families, and the system is released to the scientific community as a research product.
- Recursive-in-recursive self-improvement couples harness evolution with model RL
- Inner recursion improves harness; outer recursion trains model under improved harness
- Released as a research product spanning four scientific task families
Full article157 words · extracted from arxiv.org · click to collapse
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
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.17523