ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
摘要
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.
作者
* 共同一作
期刊/会议
引用
BibTeX
@techreport{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},
institution = {PhAI Labs},
type = {Technical Report},
number = {PHAI-TR-2026-02},
month = {September},
year = {2026},
url = {https://phai-labs.com/papers/sciencebuddy/},
note = {Version v1. Equal contribution: Shuhan Xue, Jianyuan Zhong, Ziyuan Nan}
}