ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents· ScienceBuddy：交互式科研助手的递归自改进
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,
交互式科研助手通过递归自改进提高效率和自适应性。
- 核心方法
- ScienceBuddy采用递归-in-递归自改进方法，将用户请求、反馈和执行证据转化为持续学习的任务和评估标准，通过内层递归优化框架、外层递归训练模型来实现。
- 适合谁读
- 科研人员、AI研究者
- 要解决的问题
- 论文旨在解决科研人员在日常工作中需要高效、自适应的科研助手的问题。
- 关键实验
- 提供了科研人员交互的案例研究。
- 主要贡献
- 提出了递归-in-递归自改进机制，提升了交互式科研助手的自适应性和学习效率。
- 意义与局限
- 为科研人员提供了更智能、更高效的工作辅助工具，但目前的应用场景和效果评估还较为有限。