让人类与智能体高效协作，自动匹配科研伙伴并解释决策理由。
CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration
- 双向动态匹配，通过填补能力缺口寻找合作对象。
- 两阶段排序+探索机制，在20个任务中6次超越纯贪婪策略。
- 持续更新新人能力评估，支持可解释的科学协作推荐。
基于大模型的智能体在撰写论文、编程和信息检索方面表现优异，但在科学共同体中难以形成有效协作，主要受限于双向动态交互需求及对决策可解释性的高要求。我们提出CoWeaver，一种双向、可学习且可解释的匹配算法，用于在人机协同网络中构建强合作关系。CoWeaver通过填补能力差距匹配候选者与请求者，并采用两阶段排序筛选最优人选。模型还通过不确定性感知的能力估计探索新成员，并根据请求者反馈动态更新。实验表明，结合探索（UCB）与贪婪策略的机制，在20项任务中有6项优于纯贪婪机制——这一分析上的最优解；其余任务中表现相当。在匹配质量与效率上，CoWeaver全面超越基线方法。
原文摘要 · Abstract (English)
LLM-based agents excel at writing articles, coding and information retrieval. However, they fail to form strong collaborations within the scientific community due to the bidirectional, dynamic nature of the problem and a high demand of decision interpretability. We proposed COWEAVER, a bidirectional, learnable and explainable algorithm to match scientists and form strong collaborations within a human-agent network. COWEAVER matches candidates and requesters through filling capability gaps and filters candidates through a two-stage ranking step. Finally, the model explores newcomers by maintaining uncertainty-aware capability estimates and updating them through requester's feedback. We show that the selection mechanism of combining both exploration (UCB) and greedy of COWEAVER exceeds the greedy-only mechanism - the analytical best solution - on 6 out of the 20 tasks and performed on par with the greedy-only mechanism in terms of selecting the best candidate. We compared COWEAVER baselines in terms of matching quality and efficiency. COWEAVER outperforms baselines on all metrics.
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。