MOOSE-Copilot：一个基于网络的交互式助手，用于统一探索性和细粒度科学假设发现
MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery
AI总结：
提出MOOSE-Copilot，通过形式化的人机交互协议，将发散性探索和收敛性细化统一，利用蓝图、路由和反馈三种信号引导生成，显著优于纯自主基线。
摘要：
大型语言模型（LLMs）在科学假设发现中展现出显著潜力。然而，现有方法存在两个关键限制：它们将发散性探索构思和收敛性细粒度细化视为孤立任务，并且自主运行，几乎没有人类指导。我们提出了MOOSE-Copilot，这是第一个通过形式化的人机交互（HAII）协议弥合这一抽象差距的统一框架。我们的系统使科学家能够通过三种显式信号引导生成过程：初始蓝图、阶段间路由和再生反馈。定量评估表明，注入这些结构化专家信号显著优于纯自主基线，并在神谕指导下建立了性能上限。此外，为了普及这一范式，我们开发了一个直观的基于网络界面，具有交互式树状可视化。这明确消除了复杂命令行代理工具的陡峭学习曲线，使跨学科研究人员能够直接利用、视觉编排并加速端到端的科学突破。
英文摘要：
Large language models (LLMs) show remarkable potential in scientific hypothesis discovery. However, existing approaches face two critical limitations: they treat divergent exploratory search and convergent fine-grained refinement as isolated tasks, and they operate autonomously with little to no human guidance. We present MOOSE-Copilot, the first unified framework to bridge this abstraction gap through a formalized human-AI interaction (HAII) protocol. Our system empowers scientists to steer the generative process via three explicit signals: initial blueprints, inter-stage routing, and intra-stage feedback. Using an oracle-simulated evaluation in which an LLM provides idealized expert signals, we show that injecting these structured signals significantly outperforms purely autonomous baselines, characterizing the gains achievable under high-quality guidance. Furthermore, we build a web-based interface that turns the framework into a no-code workflow: researchers pose a question, watch the hypothesis search unfold as an interactive tree, and steer it by selecting hypotheses, routing between stages, and injecting feedback-no command-line agents required. This makes end-to-end hypothesis discovery directly accessible to interdisciplinary researchers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
