ScienceBuddy：交互式科学智能体的递归内递归自我改进
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
中文总结 AI 辅助
ScienceBuddy是一个交互式科学工作空间，通过递归内递归自我改进范式，将框架演进与模型强化学习结合，持续提升科学智能体性能，并作为研究产品发布以推动发现智能。
中文摘要 AI 辅助
我们介绍并发布了ScienceBuddy，一个交互式科学研究工作空间，它将持续改进的科学智能体融入研究人员的日常工作中。ScienceBuddy支持研究人员执行科学任务，同时将其请求、反馈和执行证据转化为持续学习的任务和评估标准。其核心是递归内递归自我改进，一种将框架演进与模型强化学习相结合的范式：内层递归在模型固定的情况下改进框架，而外层递归在改进后的框架下训练模型。框架演进塑造训练经验，模型学习为框架适应创造新机会。我们展示了研究人员交互、框架改进和模型学习的案例研究，基准案例涵盖四个科学任务族。通过将ScienceBuddy作为研究产品发布，我们将这一范式提供给科学社区，并朝着发现智能迈出一步：科学AI通过与研究人员的持续合作而进步，并随着其所支持的研究而演进。网站：此HTTP URL。
英文摘要
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
