ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
ScienceBuddy released: interactive scientific agent workspace coupling harness evolution with model reinforcement learning for continual self-improvement across four scientific task families.
ScienceBuddy is an interactive scientific research workspace that turns researcher requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. Its recursive-in-recursive self-improvement paradigm couples harness evolution with the model fixed (inner recursion) and model reinforcement learning under the improved harness (outer recursion). Case studies span four scientific task families covering researcher interaction, harness refinement, and model learning. The system is released as a research product at science-buddy.io.
- Couples harness evolution with model RL in inner/outer recursion loop
- Converts researcher feedback and execution evidence into training tasks and rubrics
- Benchmark case studies span four scientific task families
- Released publicly as a research product
From the original article
1 min read at huggingface.co
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.
By Shuhan Xue, Jianyuan Zhong, Ziyuan Nan · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.