Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
- URL: http://arxiv.org/abs/2310.00280v2
- Date: Sun, 7 Apr 2024 16:20:59 GMT
- Title: Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
- Authors: Qiushi Sun, Zhangyue Yin, Xiang Li, Zhiyong Wu, Xipeng Qiu, Lingpeng Kong,
- Abstract summary: 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.
- Score: 83.4031923134958
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) are evolving at an unprecedented pace and have exhibited considerable capability in the realm of natural language processing (NLP) with world knowledge. Benefiting from ultra-large-scale training corpora, a single LLM can manage typical NLP tasks competently. However, its performance in executing reasoning tasks is still confined by the limitations of its internal representations. To push this boundary further, we introduce Corex in this paper, a suite of novel general-purpose strategies that transform LLMs into autonomous agents pioneering multi-model collaborations for complex task-solving. Inspired by human behaviors, Corex is constituted by diverse collaboration paradigms including Debate, Review, and Retrieve modes, which collectively work towards enhancing the factuality, faithfulness, and reliability of the reasoning process. These paradigms foster task-agnostic approaches that enable LLMs to ''think outside the box,'' thereby overcoming hallucinations and providing better solutions. Through extensive experiments across four different types of reasoning tasks, we demonstrate that orchestrating multiple LLMs to work in concert yields substantially better performance compared to existing methods. Further results and in-depth analysis demonstrate the cost-effectiveness of our method, facilitating collaboration among different LLMs and promoting annotation efficiency.
Related papers
- Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models [32.336273322481276]
Despite their diverse capabilities, Large Language Models (LLMs) exhibit varying strengths and weaknesses.
To address these challenges, recent studies have explored collaborative strategies for LLMs.
This paper provides a comprehensive overview of this emerging research area, highlighting the motivation behind such collaborations.
arXiv Detail & Related papers (2024-07-08T16:29:08Z) - Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks.
LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning.
We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
arXiv Detail & Related papers (2024-06-20T13:08:09Z) - Meta Reasoning for Large Language Models [58.87183757029041]
We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs)
MRP guides LLMs to dynamically select and apply different reasoning methods based on the specific requirements of each task.
We evaluate the effectiveness of MRP through comprehensive benchmarks.
arXiv Detail & Related papers (2024-06-17T16:14:11Z) - Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning [79.38140606606126]
We propose an algorithmic framework that fine-tunes vision-language models (VLMs) with reinforcement learning (RL)
Our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning.
We demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks.
arXiv Detail & Related papers (2024-05-16T17:50:19Z) - Smurfs: Leveraging Multiple Proficiency Agents with Context-Efficiency for Tool Planning [14.635361844362794]
Smurfs' is a cutting-edge multi-agent framework designed to revolutionize the application of large language models.
Smurfs can enhance the model's ability to solve complex tasks at no additional cost.
arXiv Detail & Related papers (2024-05-09T17:49:04Z) - Small LLMs Are Weak Tool Learners: A Multi-LLM Agent [73.54562551341454]
Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs.
We propose a novel approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer.
This modular framework facilitates individual updates and the potential use of smaller LLMs for building each capability.
arXiv Detail & Related papers (2024-01-14T16:17:07Z) - CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine
Chain-of-Thought Prompting for Multi-domain NLU Tasks [46.862929778121675]
Chain-of-Thought prompting is popular in reasoning tasks, but its application to Natural Language Understanding (NLU) is under-explored.
Motivated by multi-step reasoning of Large Language Models (LLMs), we propose Coarse-to-Fine Chain-of-Thought (CoF-CoT) approach.
arXiv Detail & Related papers (2023-10-23T06:54:51Z) - 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) - Examining Inter-Consistency of Large Language Models Collaboration: An
In-depth Analysis via Debate [41.949869545423375]
Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues.
To examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal, we focus on commonsense reasoning.
Our work contributes to understanding the inter-consistency among LLMs and lays the foundation for developing future collaboration methods.
arXiv Detail & Related papers (2023-05-19T11:15:33Z)
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.