Skip to content

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

Sep 2026 · arXiv.org · Vol abs/2609.17523 · 11 citations · 28 references
Computer Science

TL;DR

This work introduces and releases ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers'everyday workflows and presents case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scientific task families.

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 with the model fixed, while the outer recursion trains the model under the improved harness. Harness evolution shapes training experience, and model learning creates new opportunities for harness adaptation. We present case studies of researcher interaction, harness refinement, and model learning, with the benchmark cases spanning four scientific task families. By releasing ScienceBuddy as a research product, we make this paradigm available to the scientific community and take a step toward discovery intelligence: scientific AI that advances through sustained collaboration with researchers and evolves alongside the research it supports. Website: http://science-buddy.io

View source

Similar papers

#machine learning Preprint Oct 2026

RSIGym: A Flexible Environment for Recursive Self-Improvement

Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substantial research infrastructure. Existing settings often leave agents to rebuild routine infrastructure or restrict exploration to individual components. We introduce RSIG...

Fan-Qing Meng, Ling-Xiao Du, Hao-Cheng Lu et al. · 4 citations
#natural language process... Preprint Oct 2026

SAIL: Scientific Agentic Intelligence via a Science-Aware Loop

This work introduces SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows that achieves competitive performance across scientific research tasks with substantially fewer parameters than leading open-weight models.

Sai-Shuai Sun, Bryan Dai, Che Liu et al. · 0 citations

Learning from Research: Toward Lifelong Agent Harness Evolution

Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve the agent harness, the software that governs tool use, memory management, and task execution, while keeping the underlying language model fixed. Recent methods automat...

Jing-Bo Yang, Kwei-Herng Lai, Xiao-Wen Wang et al. · 0 citations
#artificial intelligence Review Oct 2026

RSI-Forge: From Research Papers to Environments for Recursive Self-Improvement

RSI-Forge is introduced, a multi-agent pipeline that turns published papers into executable environments for self-improvement and provides a scalable approach to constructing research environments for training and evaluating self-improving agents.

Ren-Xiong Wang, Darvin Yi, Abril Herrlein et al. · 2 citations
#artificial intelligence Review Oct 2026

AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

AReaL-RSI is presented, a framework for organizing a persistent research team of agents without updating backbone LLM weights and evaluating outcomes and whole-system resource expenditure in terms of evaluated outcomes and whole-system resource expenditure.

Wen-Hao Zhou, Jia-Jun Song, Hai-Tao Wang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments

RSIAgent is introduced, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction that substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6.3.

Si-Bo Zhu, Shi-Cheng Fan, Xin-Yue Wang et al. · 10 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.