AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Consensus-Driven Multi-Agent Cognitive Reasoning for Enhancing the Emotional Intelligence of Large Language Models

Geng Tu, Dingming Li, Jun Huang, Ruifeng Xu

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: Self-evolving language agent learning · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MACRo, a consensus-driven multi-agent cognitive reasoning framework to improve the emotional intelligence of LLMs on EmoBench-style tasks.

Problem

LLMs remain limited in emotional intelligence, particularly on cognitively demanding tasks requiring inference of others' latent mental states, intentions, and emotions in nuanced social contexts (as benchmarked by EmoBench).

Approach

A multi-agent cognitive reasoning framework (MACRo) in which multiple agents reason about social-emotional scenarios and reach consensus to improve EI reasoning; details beyond the abstract are unavailable.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add MACRo CogCoT promptBaichuan2-53B · EmoBench EU overall (English)accuracy (%): 34.88 -> 47.62Improved
add MACRo CogCoT promptDeepSeek-V3 · EmoBench EU overall (English)accuracy (%): 57.50 -> 58.62Improved
add MACRo CogCoT promptBaichuan2-Chat-7B · EmoBench EU overall (English)accuracy (%): 22.38 -> 14.62Hurt
add MACRo CogCoT promptBaichuan2-Chat-13B · EmoBench EU overall (English)accuracy (%): 26.25 -> 22.50Hurt
add MACRo CogCoT promptLlama2-Chat-13B · EmoBench EU overall (English)accuracy (%): 17.38 -> 16.00No clear effect
add MACRo CogCoT promptQwen-Chat-14B · EmoBench EA overall (English)accuracy (%): 60.50 -> 58.75Hurt
add MACRo CogCoT promptBaichuan2-53B · EmoBench EA overall (English)accuracy (%): 65.38 -> 74.25Improved
add MACRo CogCoT prompt (general)11 LLMs · EmoBench EU/EA (EN, ZH)accuracy (%): Baichuan2-Chat-7B EU EN 22.38 -> 14.62; Baichuan2-53B EU EN 34.88 -> 47.62Mixed
add consensus game (ablation)MACRo (ChatGLM3-6B) · EmoBench EU overall (English)accuracy (%): 22.75 -> 24.50Improved
add consensus game (ablation)MACRo (DeepSeek-V3) · EmoBench EU overall (English)accuracy (%): 57.75 -> 58.62Improved
add multi-agent role specialization (ablation)MACRo (ChatGLM3-6B) · EmoBench EU overall (English)accuracy (%): 20.38 -> 24.50Improved
use zero-shot MACRo CogCoT instead of trained COLM chainsLlama2-Chat-7B · EmoBench EA overall (Chinese)accuracy (%): 31.75 -> 44.75Improved

Experimental setup

Datasets: EmoBench

Benchmarks: EmoBench

Builds on: EmoBench

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy