AI 中文总结
该研究针对AI辅助研究构思的同质化问题，提出DivAlign四阶段流程，在保留研究者-方向适配性的同时降低社区研究组合冗余，相关成果代码与数据已公开。
AI 中文摘要
AI辅助研究构思已成为加速科学发现的有前景范式，现有系统能够生成基于论文、主题或轻量研究者上下文的研究方向。然而当前系统大多孤立优化个体建议，存在两个盲区：一是粗糙的研究者表示可能引出看似广泛可行但缺乏足够研究者特定基础的主流方向；二是独立推荐会将社区的研究组合集中在重复出现的高概率主题上。为解决这些盲区，我们提出DivAlign，一种用于保持对齐的去同质化四阶段流程：DivAlign提取细粒度研究者画像，生成画像条件化的候选方向，沿三个对齐维度（可执行性、可理解性和增长潜力）对其打分，并呈现研究者局部方向同时减少社区研究组合的冗余。在我们从五个子领域的95名AI研究者构建的基准上，DivAlign在保留研究者-方向适配性的同时降低了社区级冗余：与粗糙单次构思相比，它将平均成对相似度从0.331降至0.294，最近邻相似度从0.704降至0.608；与独立最优选择变体相比，DivAlign在保留99.9%研究者-方向适配分数的同时，将最近邻相似度从0.663降至0.608。代码和数据可在指定URL获取。
英文摘要
AI-assisted research ideation has emerged as a promising paradigm for accelerating scientific discovery, with systems now capable of generating research directions conditioned on papers, topics, or lightweight researcher contexts. Yet current systems largely optimize individual suggestions in isolation. This leaves two blind spots. First, coarse researcher representations may elicit mainstream directions that appear broadly feasible, but lack sufficient researcher-specific grounding. Second, independent recommendations can concentrate a community's portfolio around recurring high-probability themes. To address these blind spots, we propose DivAlign, a four-stage pipeline for alignment-preserving de-homogenization. DivAlign extracts fine-grained researcher profiles, generates profile-conditioned candidate directions, scores them along three alignment dimensions (Executability, Comprehensibility, and Growth Potential), and surfaces researcher-local directions while reducing redundancy across the community portfolio. On a benchmark we construct from 95 AI researchers across five subfields, DivAlign reduces community-level redundancy while preserving researcher-direction fit. Compared with coarse single-shot ideation, it lowers average pairwise similarity from 0.331 to 0.294 and nearest-neighbor similarity from 0.704 to 0.608. Compared with the independent top-choice variant, DivAlign reduces nearest-neighbor similarity from 0.663 to 0.608 while retaining 99.9% of the researcher-direction fit score. Code and data are available at https://github.com/Ruixxxx/DivAlign.
