EN 立即申请

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

下载 PDF9 月 16 日发布 GitHub9 月 16 日发布 引用

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

Shuhan Xue*, Jianyuan Zhong*, Ziyuan Nan*, Wenbin Li, Zhaochen Yu, Jinchao Ding, Qiang Gao, Pengyu Zhan, Yuntong Zhang, Tian Cheng, Zhenfei Yin, Yingcheng Wu, Ling Yang

* 共同一作

期刊/会议

PhAI Labs Technical Report

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}
}

← 全部论文