When Should We Orchestrate Multiple Agents?

Adrian Weller; Andrew Gordon Wilson; Francesco Quinzan; Ilia Sucholutsky; Katherine M. Collins; Mihir Upadhyay; Muhammad Bilal Zafar; Sanyam Kapoor; Umang Bhatt

arxiv: 2503.13577 · v1 · pith:J3UCALAYnew · submitted 2025-03-17 · 💻 cs.MA · cs.CY· cs.LG

When Should We Orchestrate Multiple Agents?

Umang Bhatt , Sanyam Kapoor , Mihir Upadhyay , Ilia Sucholutsky , Francesco Quinzan , Katherine M. Collins , Adrian Weller , Andrew Gordon Wilson

show 1 more author

Muhammad Bilal Zafar

This is my paper

classification 💻 cs.MA cs.CYcs.LG

keywords agentsmultipleorchestrationcostorchestrateperformanceartificialavailability

0 comments

read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

A Survey of Context Engineering for Large Language Models
cs.CL 2025-07 accept novelty 4.0

The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle...