让智能体按能力分配预测任务，提升整体性能
Learning to Assign Prediction Tasks to Agents with Capacity Constraints
- 基于任务上下文动态分配预测任务给有容量限制的智能体
- 在表格、图像和文本任务上显著优于不考虑上下文的基线方法
- 适用于人机混合系统，尤其适合大模型与人类协作场景
我们研究从一组可用的人类或AI智能体中学习如何为单一任务分配最优智能体。重点在于顺序学习智能体专长和分配策略，每个智能体仅能处理部分任务。我们从智能体容量、专长差异和任务上下文三方面对问题进行理论刻画，并提出一种序列式探索-利用策略学习框架，旨在最大化整体性能。在多种表格、图像和文本预测任务上的实验表明，相较于非上下文基线，该策略学习算法在不同类型的智能体（包括大语言模型和人类）上均展现出系统性性能提升。
原文摘要 · Abstract (English)
We address the problem of learning to assign prediction tasks to one agent from a set of available human or AI agents. In particular, we focus on the sequential learning of agent expertise and assignment policies where each agent is constrained to handle a fraction of tasks. We provide a general theoretical characterization of this problem in terms of agent capacities, differences in agent expertise, and task context. We then develop a framework of sequential explore-exploit policy-learning algorithms that seek to maximize overall performance. Experimental results over a variety of tabular, image, and text prediction tasks demonstrate systematic gains from our policy-learning algorithms relative to non-contextual baselines across different types of agents, including LLMs and humans.
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。