让论文想法在测试时像进化一样不断优化，更创新多样。
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
- 用流动引导的搜索扩展文献路径，动态生成高质量初始想法。
- 测试时模拟进化过程，融合跨领域知识，提升想法新颖性和可行性。
- 适合需要突破性创意的科研自动化场景，尤其擅长复杂问题探索。
科学想法生成（SIG）对人工智能驱动的自主研究至关重要，但现有方法常受限于静态的检索-生成范式，导致想法同质且缺乏多样性。本文提出FlowPIE，一种紧密耦合的检索-生成框架，将文献探索与想法生成视为协同演化过程。FlowPIE通过受GFlowNets启发的流引导蒙特卡洛树搜索（MCTS）扩展文献轨迹，利用基于大语言模型的生成奖励模型（GRM）评估当前想法质量，作为监督信号指导自适应检索，构建多样且高质量的初始种群。在此基础上，FlowPIE将想法生成建模为测试时的进化过程，结合隔离岛范式与GRM驱动的适应度计算，实现选择、交叉和变异操作，有效缓解过度依赖参数化知识与静态文献带来的信息茧房问题。大量实验表明，相较于强基线的LLM与代理框架，FlowPIE持续生成更具新颖性、可行性和多样性的想法，同时支持测试时奖励缩放。
原文摘要 · Abstract (English)
Scientific idea generation (SIG) is critical to AI-driven autonomous research, yet existing approaches are often constrained by a static retrieval-then-generation paradigm, leading to homogeneous and insufficiently divergent ideas. In this work, we propose FlowPIE, a tightly coupled retrieval-generation framework that treats literature exploration and idea generation as a co-evolving process. FlowPIE expands literature trajectories via a flow-guided Monte Carlo Tree Search (MCTS) inspired by GFlowNets, using the quality of current ideas assessed by an LLM-based generative reward model (GRM) as a supervised signal to guide adaptive retrieval and construct a diverse, high-quality initial population. Based on this population, FlowPIE models idea generation as a test-time idea evolution process, applying selection, crossover, and mutation with the isolation island paradigm and GRM-based fitness computation to incorporate cross-domain knowledge. It effectively mitigates the information cocoons arising from over-reliance on parametric knowledge and static literature. Extensive evaluations demonstrate that FlowPIE consistently produces ideas with higher novelty, feasibility and diversity compared to strong LLM-based and agent-based frameworks, while enabling reward scaling during test time.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。