When Should We Orchestrate Multiple Agents?
- URL: http://arxiv.org/abs/2503.13577v1
- Date: Mon, 17 Mar 2025 14:26:07 GMT
- Title: When Should We Orchestrate Multiple Agents?
- Authors: Umang Bhatt, Sanyam Kapoor, Mihir Upadhyay, Ilia Sucholutsky, Francesco Quinzan, Katherine M. Collins, Adrian Weller, Andrew Gordon Wilson, Muhammad Bilal Zafar,
- Abstract summary: Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration.<n>We design a framework to orchestrate agents under realistic conditions, such as inference costs or availability constraints.<n>We show theoretically that orchestration is only effective if there are performance or cost differentials between agents.
- Score: 74.27052374196269
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- Don't lie to your friends: Learning what you know from collaborative self-play [90.35507959579331]
We propose a radically new approach to teaching AI agents what they know.<n>We construct multi-agent collaborations in which the group is rewarded for collectively arriving at correct answers.<n>The desired meta-knowledge emerges from the incentives built into the structure of the interaction.
arXiv Detail & Related papers (2025-03-18T17:53:20Z) - Affordable Generative Agents [16.372072265248192]
Affordable Generative Agents (AGA) is a framework for enabling the generation of believable and low-cost interactions on both agent-environment and inter-agents levels.
Our code is publicly available at: https://github.com/AffordableGenerativeAgents/Affordable-Generative-Agents.
arXiv Detail & Related papers (2024-02-03T06:16:28Z) - ProAgent: Building Proactive Cooperative Agents with Large Language
Models [89.53040828210945]
ProAgent is a novel framework that harnesses large language models to create proactive agents.
ProAgent can analyze the present state, and infer the intentions of teammates from observations.
ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
arXiv Detail & Related papers (2023-08-22T10:36:56Z) - AgentVerse: Facilitating Multi-Agent Collaboration and Exploring
Emergent Behaviors [93.38830440346783]
We propose a multi-agent framework framework that can collaboratively adjust its composition as a greater-than-the-sum-of-its-parts system.
Our experiments demonstrate that framework framework can effectively deploy multi-agent groups that outperform a single agent.
In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups.
arXiv Detail & Related papers (2023-08-21T16:47:11Z) - Decentralized scheduling through an adaptive, trading-based multi-agent
system [1.7403133838762448]
In multi-agent reinforcement learning systems, the actions of one agent can have a negative impact on the rewards of other agents.
This work applies a trading approach to a simulated scheduling environment, where the agents are responsible for the assignment of incoming jobs to compute cores.
The agents can trade the usage right of computational cores to process high-priority, high-reward jobs faster than low-priority, low-reward jobs.
arXiv Detail & Related papers (2022-07-05T13:50:18Z) - LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent
Reinforcement Learning [122.47938710284784]
We propose a novel framework for learning dynamic subtask assignment (LDSA) in cooperative MARL.
To reasonably assign agents to different subtasks, we propose an ability-based subtask selection strategy.
We show that LDSA learns reasonable and effective subtask assignment for better collaboration.
arXiv Detail & Related papers (2022-05-05T10:46:16Z) - Multi-agent Actor-Critic with Time Dynamical Opponent Model [16.820873906787906]
In multi-agent reinforcement learning, multiple agents learn simultaneously while interacting with a common environment and each other.
We propose a novel textitTime Dynamical Opponent Model (TDOM) to encode the knowledge that the opponent policies tend to improve over time.
We show empirically that TDOM achieves superior opponent behavior prediction during test time.
arXiv Detail & Related papers (2022-04-12T07:16:15Z) - Coach-assisted Multi-Agent Reinforcement Learning Framework for
Unexpected Crashed Agents [120.91291581594773]
We present a formal formulation of a cooperative multi-agent reinforcement learning system with unexpected crashes.
We propose a coach-assisted multi-agent reinforcement learning framework, which introduces a virtual coach agent to adjust the crash rate during training.
To the best of our knowledge, this work is the first to study the unexpected crashes in the multi-agent system.
arXiv Detail & Related papers (2022-03-16T08:22:45Z) - Exploring the Impact of Tunable Agents in Sequential Social Dilemmas [0.0]
We leverage multi-objective reinforcement learning to create tunable agents.
We apply this technique to sequential social dilemmas.
We demonstrate that the tunable agents framework allows easy adaption between cooperative and competitive behaviours.
arXiv Detail & Related papers (2021-01-28T12:44:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.