Learning to Assign Prediction Tasks to Agents with Capacity Constraints
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914607030861824 |
|---|---|
| author | Wu, Shang Kher, Saatvik Smyth, Padhraic |
| author_facet | Wu, Shang Kher, Saatvik Smyth, Padhraic |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27999 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning to Assign Prediction Tasks to Agents with Capacity Constraints Wu, Shang Kher, Saatvik Smyth, Padhraic Human-Computer Interaction Artificial Intelligence 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. |
| title | Learning to Assign Prediction Tasks to Agents with Capacity Constraints |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2605.27999 |