ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
A scientist and an AI partner talk it through; every follow-up, edit and acceptance is written down, and the AI's workspace gets better round by round.
Move the cursor over the diagram
Overview
AI research partner
An interactive Scientific Agent: recursive self-improvement in real research interaction, exploring Recursive-in-Recursive Self-Improvement (RSI in RSI).
ScienceBuddy is an independent research and engineering exploration built around interaction with scientists, research feedback and the continual improvement of agents, in the Discovery Intelligence direction DFM is about.
It focuses on an interactive form of Science RSI: a user poses a scientific question, the agent calls tools and answers; the scientist's follow-ups, edits, acceptances, rejections and re-runs become feedback that drives the research agent's workspace and harness to keep evolving.
What ScienceBuddy produces is not only one-off answers but the feedback, research trajectories, tool calls and task states of the interaction. In future these can be organised into reusable scientific tasks and environments for reinforcement learning or other model training.
It takes in and structures
- Scientific questions
- Data needs
- Research materials
- Literature and code
- Scientific tool calls
- Hypothesis formation and testing
- What the following research workflow needs
An early product / research preview: the capabilities opened, demonstrations and entry points follow the actual version. The product entry opened on 16 September.
Abstract
ScienceBuddy is an interactive scientific research workspace that brings continually improving agents into a researcher's everyday work. It supports researchers in carrying out scientific tasks while turning their requests, feedback and execution evidence into tasks and evaluation rubrics for continual learning. At its core is recursive-in-recursive self-improvement, which couples harness evolution with model reinforcement learning: the inner recursion improves the harness with the model fixed, and the outer recursion trains the model under the improved harness. Case studies cover researcher interaction, harness refinement and model learning across four families of scientific task.
Authors
* Equal contribution
Venue
Cite
BibTeX
@article{xue2026sciencebuddy,
title={ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents},
author={Xue, Shuhan and Zhong, Jianyuan and Nan, Ziyuan and Li, Wenbin and Yu, Zhaochen and Ding, Jinchao and Gao, Qiang and Zhan, Pengyu and Zhang, Yuntong and Cheng, Tian and Yin, Zhenfei and Wu, Yingcheng and Yang, Ling},
journal={arXiv preprint arXiv:2609.17523},
year={2026}
}