paper-with-me

홈 › Papers

When Should We Orchestrate Multiple Agents?

2025-03-17 · Umang Bhatt, Sanyam Kapoor, Mihir Upadhyay, Ilia Sucholutsky, Francesco Quinzan, Katherine M. Collins, Adrian Weller, Andrew Gordon Wilson, Muhammad Bilal Zafar

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.

📄 PDF Abstract BibTeX arXiv:2503.13577

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Goals are Enough: Inducing AdHoc cooperation among unseen Multi-Agent systems in IMFs

2023-10-26 · Kaushik Dey, Satheesh K. Perepu, Abir Das

Intent-based management will play a critical role in achieving customers' expectations in the next-generation mobile networks. Traditional methods cannot perform efficient resource management since they tend to handle ea…

ManagementMulti-agent Reinforcement Learning

Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives

2025-02-04 · Elliot Meyerson, Xin Qiu

Decomposing hard problems into subproblems often makes them easier and more efficient to solve. With large language models (LLMs) crossing critical reliability thresholds for a growing slate of capabilities, there is an …

Position

COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context

2025-10-06 · Naman Gupta, Shreeyash Gowaikar, Arun Iyer, Kirankumar Shiragur 외 arxiv

Reasoning over very long inputs remains difficult for large language models (LLMs). Common workarounds either shrink the input via retrieval (risking missed evidence), enlarge the context window (straining selectivity), …

EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning

2026-04-10 · Tiantian He, Yihang Chen, Keyue Jiang, Ka Yiu Lee 외 arxiv

Computer-use agents that combine GUI interaction with structured API calls via the Model Context Protocol (MCP) show promise for automating software tasks. However, existing approaches lack a principled understanding of …

Wavefield Networked Sensing: Principles, Algorithms and Applications

2023-05-17 · Marco Manzoni, Dario Tagliaferri, Stefano Tebaldini, Marouan Mizmizi 외

Networked sensing refers to the capability of properly orchestrating multiple sensing terminals to enhance specific figures of merit, e.g., positioning accuracy or imaging resolution. Regarding radio-based sensing, it is…

valid