Controlling Large Language Model-based Agents for Large-Scale
Decision-Making: An Actor-Critic Approach
- URL: http://arxiv.org/abs/2311.13884v3
- Date: Tue, 23 Jan 2024 14:11:04 GMT
- Title: Controlling Large Language Model-based Agents for Large-Scale
Decision-Making: An Actor-Critic Approach
- Authors: Bin Zhang, Hangyu Mao, Jingqing Ruan, Ying Wen, Yang Li, Shao Zhang,
Zhiwei Xu, Dapeng Li, Ziyue Li, Rui Zhao, Lijuan Li, Guoliang Fan
- Abstract summary: We develop a modular framework called LLaMAC to address hallucination in Large Language Models and coordination in Multi-Agent Systems.
LLaMAC implements a value distribution encoding similar to that found in the human brain, utilizing internal and external feedback mechanisms to facilitate collaboration and iterative reasoning among its modules.
- Score: 28.477463632107558
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The remarkable progress in Large Language Models (LLMs) opens up new avenues
for addressing planning and decision-making problems in Multi-Agent Systems
(MAS). However, as the number of agents increases, the issues of hallucination
in LLMs and coordination in MAS have become increasingly prominent.
Additionally, the efficient utilization of tokens emerges as a critical
consideration when employing LLMs to facilitate the interactions among a
substantial number of agents. In this paper, we develop a modular framework
called LLaMAC to mitigate these challenges. LLaMAC implements a value
distribution encoding similar to that found in the human brain, utilizing
internal and external feedback mechanisms to facilitate collaboration and
iterative reasoning among its modules. Through evaluations involving system
resource allocation and robot grid transportation, we demonstrate the
considerable advantages afforded by our proposed approach.
Related papers
- Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.
We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems.
Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
arXiv Detail & Related papers (2024-05-23T08:33:19Z) - CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models [3.2186308082558623]
We introduce the TinyAgent model, trained on a meticulously curated high-quality dataset.
We also present the Collaborative Multi-Agent Tuning (CMAT) framework, an innovative system designed to augment language agent capabilities.
In this research, we propose a new communication agent framework that integrates multi-agent systems with environmental feedback mechanisms.
arXiv Detail & Related papers (2024-04-02T06:07:35Z) - Large Multimodal Agents: A Survey [78.81459893884737]
Large language models (LLMs) have achieved superior performance in powering text-based AI agents.
There is an emerging research trend focused on extending these LLM-powered AI agents into the multimodal domain.
This review aims to provide valuable insights and guidelines for future research in this rapidly evolving field.
arXiv Detail & Related papers (2024-02-23T06:04:23Z) - Theory of Mind for Multi-Agent Collaboration via Large Language Models [5.2767999863286645]
This study evaluates Large Language Models (LLMs)-based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks.
We observed evidence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents.
arXiv Detail & Related papers (2023-10-16T07:51:19Z) - LanguageMPC: Large Language Models as Decision Makers for Autonomous
Driving [87.1164964709168]
This work employs Large Language Models (LLMs) as a decision-making component for complex autonomous driving scenarios.
Extensive experiments demonstrate that our proposed method not only consistently surpasses baseline approaches in single-vehicle tasks, but also helps handle complex driving behaviors even multi-vehicle coordination.
arXiv Detail & Related papers (2023-10-04T17:59:49Z) - Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration [83.4031923134958]
Corex is a suite of novel general-purpose strategies that transform Large Language Models into autonomous agents.
Inspired by human behaviors, Corex is constituted by diverse collaboration paradigms including Debate, Review, and Retrieve modes.
We demonstrate that orchestrating multiple LLMs to work in concert yields substantially better performance compared to existing methods.
arXiv Detail & Related papers (2023-09-30T07:11:39Z) - Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation [52.930183136111864]
We propose using scorable negotiation to evaluate Large Language Models (LLMs)
To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities.
We provide procedures to create new games and increase games' difficulty to have an evolving benchmark.
arXiv Detail & Related papers (2023-09-29T13:33:06Z) - PooL: Pheromone-inspired Communication Framework forLarge Scale
Multi-Agent Reinforcement Learning [0.0]
textbfPooL is an indirect communication framework applied to large scale multi-agent reinforcement textbfl.
PooL uses the release and utilization mechanism of pheromones to control large-scale agent coordination.
PooL can capture effective information and achieve higher rewards than other state-of-arts methods with lower communication costs.
arXiv Detail & Related papers (2022-02-20T03:09:53Z) - Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems.
Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC.
We provide a practical parametrization of the core optimization problem.
arXiv Detail & Related papers (2021-07-08T18:01:02Z) - Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn
an Adaptive Sparse Communication Graph [39.48317026356428]
The complexity of multiagent reinforcement learning increases exponentially with respect to the agent number.
One critical feature in MARL that is often neglected is that the interactions between agents are quite sparse.
We propose an adaptive sparse attention mechanism by generalizing a sparsity-inducing activation function.
We show that our algorithm can learn an interpretable sparse structure and outperforms previous works by a significant margin on applications involving a large-scale multiagent system.
arXiv Detail & Related papers (2020-03-02T17:18:25Z)
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.