通过跨研究路径推理，自动发现有创新性的科研选题。
Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolution
- 构建分支演化轨迹，追踪方法、问题与空白的演变。
- 在6个AI领域中生成想法得分达6.27，优于基线5.36。
- 适合想突破思维定式、寻找交叉创新点的研究者。
有效的科研选题需要超越对已有工作的静态理解，追踪研究问题与解决方案在文献中的演进过程。现有方法或把论文视为非结构化上下文，或仅将学术演化建模为孤立的引用链，忽略了不同研究路径间的交互。我们提出Tree-of-Ideas（ToI），一种两阶段框架：EvoTrace从引用中重构分叉的学术演化轨迹，追踪演进的方法、已解决的问题和未填补的空白；EvoAgent则在多条轨迹间进行推理，识别趋同的问题与互补的解决方案，生成有依据的研究构想。在六个AI研究主题上，ToI在自动方法中得分最高（10分制下为6.27），显著优于最强基线（5.36），且新颖性（6.36）与根基性（7.00）均表现优异。其得分接近人类参考论文水平（6.29），验证了跨路径演化推理的价值。
原文摘要 · Abstract (English)
Effective research ideation requires moving beyond a static understanding of prior work to trace how research problems and solutions evolve across the literature. Existing methods either treat papers as unstructured context or model scholarly evolution as isolated citation chains, overlooking interactions among research trajectories. We propose Tree-of-Ideas (ToI), a two-stage framework. EvoTrace reconstructs branching scholarly trajectories from citations, tracking evolving methods, resolved problems, and gaps. EvoAgent then reasons across trajectories to identify convergent problems and complementary solutions, generating grounded research ideas. Across six AI research topics, ToI achieves the highest score among automatic methods (6.27 vs. 5.36 for the strongest baseline on a 10-point scale), with strong Novelty (6.36) and Groundedness (7.00). Also, its score approaches that of human-paper references (6.29), demonstrating the value of cross-path evolutionary reasoning.
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。