AIMAJul 5, 2025

CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate

arXiv:2507.03928v14 citationsh-index: 4ACL
Originality Incremental advance
AI Analysis

This addresses inefficiencies in multi-agent systems for AI, though it is an incremental improvement over existing MAD methods.

The paper tackles the issues of lengthy input contexts and overconfidence in Multi-Agent Debate (MAD) by proposing CortexDebate, a method that constructs a sparse debating graph among LLM agents, resulting in improved performance across eight datasets from four task types.

Nowadays, single Large Language Model (LLM) struggles with critical issues such as hallucination and inadequate reasoning abilities. To mitigate these issues, Multi-Agent Debate (MAD) has emerged as an effective strategy, where LLM agents engage in in-depth debates with others on tasks. However, existing MAD methods face two major issues: (a) too lengthy input contexts, which causes LLM agents to get lost in plenty of input information and experiences performance drop; and (b) the overconfidence dilemma, where self-assured LLM agents dominate the debate, leading to low debating effectiveness. To address these limitations, we propose a novel MAD method called "CortexDebate". Inspired by the human brain's tendency to establish a sparse and dynamically optimized network among cortical areas governed by white matter, CortexDebate constructs a sparse debating graph among LLM agents, where each LLM agent only debates with the ones that are helpful to it. To optimize the graph, we propose a module named McKinsey-based Debate Matter (MDM), which acts as an artificial analog to white matter. By integrating the McKinsey Trust Formula, a well-established measure of trustworthiness from sociology, MDM enables credible evaluations that guide graph optimization. The effectiveness of our CortexDebate has been well demonstrated by extensive experimental results across eight datasets from four task types.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes