Year: 2025
Type: preprint
Abstract: Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration. We design a framework to orchestrate agents under realistic conditions, such as inference costs or availability constraints. We show theoretically that orchestration is only effective if there are performance or cost differentials between agents. We then empirically demonstrate how orchestration between multiple agents can be helpful for selecting agents in a simulated environment, picking a learning strategy in the infamous Rogers' Paradox from social science, and outsourcing tasks to other agents during a question-answer task in a user study.
Source: arXiv (Cornell University)
Authors: Bhatt, Umang, Kapoor, Sanyam, Upadhyay, Mihir, Sucholutsky, Ilia, Quinzan, Francesco, Collins, Katherine M., Weller, Adrian, Wilson, Andrew Gordon, Zafar, Muhammad Bilal
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6948306875
Cites:
Cited by:
Related to: