Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models

• URL: http://arxiv.org/abs/2410.20007v1
• Date: Fri, 25 Oct 2024 23:32:48 GMT
• Title: Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models
• Authors: Danqing Wang, Zhuorui Ye, Fei Fang, Lei Li,
• Abstract summary: This paper proposes a novel cooperative multi-agent reasoning framework (CoPlanner) CoPlanner consists of two LLM agents: a planning agent and a reasoning agent. Our results demonstrate that the guidance from the planning agent and the effective cooperation between the agents contribute to the superior performance of CoPlanner.
• Score: 37.899581994741865
• License:
• Abstract: Enhancing the reasoning capabilities of large language models (LLMs) is crucial for enabling them to tackle complex, multi-step problems. Multi-agent frameworks have shown great potential in enhancing LLMs' reasoning capabilities. However, the lack of effective cooperation between LLM agents hinders their performance, especially for multi-step reasoning tasks. This paper proposes a novel cooperative multi-agent reasoning framework (CoPlanner) by separating reasoning steps and assigning distinct duties to different agents. CoPlanner consists of two LLM agents: a planning agent and a reasoning agent. The planning agent provides high-level strategic hints, while the reasoning agent follows these hints and infers answers. By training the planning agent's policy through the interactive reasoning process via Proximal Policy Optimization (PPO), the LLaMA-3-8B-based CoPlanner outperforms the previous best method by 9.94\% on LogiQA and 3.09\% on BBH. Our results demonstrate that the guidance from the planning agent and the effective cooperation between the agents contribute to the superior performance of CoPlanner in tackling multi-step reasoning problems.

Related papers

• CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation [98.11670473661587]
  CaPo improves cooperation efficiency with two phases: 1) meta-plan generation, and 2) progress-adaptive meta-plan and execution. Experimental results on the ThreeDworld Multi-Agent Transport and Communicative Watch-And-Help tasks demonstrate that CaPo achieves much higher task completion rate and efficiency compared with state-of-the-arts.
  arXiv  Detail & Related papers  (2024-11-07T13:08:04Z)
• Agent-Oriented Planning in Multi-Agent Systems [54.429028104022066]
  We propose a novel framework for agent-oriented planning in multi-agent systems, leveraging a fast task decomposition and allocation process. We integrate a feedback loop into the proposed framework to further enhance the effectiveness and robustness of such a problem-solving process.
  arXiv  Detail & Related papers  (2024-10-03T04:07:51Z)
• Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation [49.27250832754313]
  We present AgentCOT, a llm-based autonomous agent framework. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. We introduce two new strategies to enhance the performance of AgentCOT.
  arXiv  Detail & Related papers  (2024-09-19T02:20:06Z)
• Cooperative Reward Shaping for Multi-Agent Pathfinding [4.244426154524592]
  The primary objective of Multi-Agent Pathfinding (MAPF) is to plan efficient and conflict-free paths for all agents. Traditional multi-agent path planning algorithms struggle to achieve efficient distributed path planning for multiple agents. This letter introduces a unique reward shaping technique based on Independent Q-Learning (IQL)
  arXiv  Detail & Related papers  (2024-07-15T02:44:41Z)
• Adaptive In-conversation Team Building for Language Model Agents [33.03550687362213]
  Leveraging multiple large language model (LLM) agents has shown to be a promising approach for tackling complex tasks. Our new adaptive team-building paradigm offers a flexible solution, realized through a novel agent design named Captain Agent. A comprehensive evaluation across six real-world scenarios demonstrates that Captain Agent significantly outperforms existing multi-agent methods.
  arXiv  Detail & Related papers  (2024-05-29T18:08:37Z)
• A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models [15.874604623294427]
  Multi-Phases planning problem involves multiple interconnected stages, such as outlining, information gathering, and planning. Existing reasoning approaches have struggled to effectively address this complex task. Our research aims to address this challenge by developing a human-like planning framework for LLM agents.
  arXiv  Detail & Related papers  (2024-05-28T14:13:32Z)
• 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)
• KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents [54.09074527006576]
  Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges. This inadequacy primarily stems from the lack of built-in action knowledge in language agents. We introduce KnowAgent, a novel approach designed to enhance the planning capabilities of LLMs by incorporating explicit action knowledge.
  arXiv  Detail & Related papers  (2024-03-05T16:39:12Z)
• 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)
• Improving Planning with Large Language Models: A Modular Agentic Architecture [7.63815864256878]
  Large language models (LLMs) often struggle with tasks that require multi-step reasoning or goal-directed planning. We propose an agentic architecture, the Modular Agentic Planner (MAP), in which planning is accomplished via the recurrent interaction of specialized modules. We find that MAP yields significant improvements over both standard LLM methods.
  arXiv  Detail & Related papers  (2023-09-30T00:10:14Z)

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.