Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration

Qiushi Sun, Zhangyue Yin, Xiang Li, Zhiyong Wu, Xipeng Qiu, Lingpeng Kong

Research Area: LMs and the world, LMs and interactions

Keywords: Model Collaborations; Complex Reasoning; Large Language Models

TL;DR: We introduce Corex, a suite of strategies designed to enhance the capabilities of LLMs in complex task-solving, with a pivotal focus on advancing multi-model collaboration.

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 complex tasks is still confined by the limitations of its internal representation. To push this boundary further, we introduce Corex, a suite of novel general-purpose strategies that transform LLMs into autonomous agents, pioneering multi-model collaborations for task-solving. Inspired by human behaviors, Corex is constituted by diverse collaboration paradigms including Discuss, Review, and Retrieve modes, which collectively work towards enhancing the reasoning process. These paradigms foster task-agnostic approaches that enable LLMs to “think outside the box,” thereby overcoming common errors and providing better solutions. Through extensive experiments across four different types of reasoning tasks, we demonstrate that orchestrating multiple LLM-based agents to work in concert yields better results compared to well-established existing baselines. Further analysis reveals the advantages of Corex over other multi-model methods, synergies produced among different LLMs, and the effectiveness across various aspects.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 366