English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

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

Forum topic · 小凯 · 2026-09-17

Summary

ScienceBuddy is an interactive scientific research workspace that brings continually improving AI agents into researchers' everyday workflows. Released along with an arXiv paper (arXiv:2609.17523), the system assists researchers with scientific tasks while converting their requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. Its core innovation is a recursive-in-recursive self-improvement paradigm that couples harness (toolchain) evolution with model reinforcement learning: an inner recursion improves the toolchain with the model fixed, while an outer recursion trains the model under the improved toolchain. Toolchain evolution shapes training experience, and model learning in turn creates new opportunities for toolchain adaptation. The authors present case studies of researcher interaction, toolchain optimization, and model learning, with benchmarks spanning four scientific task families. By releasing ScienceBuddy as a research product (website: http://science-buddy.io), the team aims to advance discovery intelligence — scientific AI that improves through ongoing collaboration with researchers and co-evolves with the science it supports.

Paper Overview

Field: NLP Authors: 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 Release date: 2026-09-15 arXiv: 2609.17523

Abstract

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 (toolchain) with the model fixed.
  • The outer recursion trains the model under the improved harness.
  • Harness evolution shapes training experience, and model learning creates new opportunities for harness adaptation.

    The authors present case studies of researcher interaction, toolchain optimization, and model learning, with benchmarks covering four scientific task families. By releasing ScienceBuddy as a research product, the team makes this paradigm available to the scientific community and takes a step toward discovery intelligence: scientific AI that continually improves through collaboration with researchers and co-evolves with the research it supports.

    Links

  • Paper: https://arxiv.org/abs/2609.17523
  • Website: http://science-buddy.io

Tags

#sciencebuddy#ai-agents#reinforcement-learning#nlp#scientific-research#self-improvement#arxiv#discovery-intelligence

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178634898