AI Paper Atlas

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

Analyze–Compose–Execute: A Dynamic Dialogue Framework for Multi-Agent Debate

Wenyuan Gu, Haowen Wang, Jiale Han, Xiang Li, Zhixuan Wu, Hongru Xiao, Bo Cheng

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: LLM multi-agent decision making

Read the paper

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 a dynamic dialogue framework for multi-agent debate that adapts discussion acts across rounds instead of following fixed pipelines.

Problem

Current multi-agent debate (MAD) methods constrain LLM agents to fixed discussion pipelines that repeat the same discussion act for a predetermined number of rounds, limiting effectiveness and adaptivity.

Approach

Replaces fixed MAD pipelines with a dynamic dialogue framework (Analyze, Compose, Execute) in which agents choose and sequence discussion acts adaptively; details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dynamic Analyze-Compose-Execute debate instead of fixed pipelinesMAD with GPT-3.5-turbo · BBH 23 tasks avgaccuracy (%): 52.5 -> 61.0 (best baseline RTC vs ACE)Improved
add Analyze module (ablation)ACE · BBH Penguins in a Tableaccuracy (%): 60.3 -> 70.1Improved
add Analyze module (ablation)ACE · BBH Tracking Shuffled Objectsaccuracy (%): 23.1 -> 37.1Improved
add guided Compose instead of random act selection (ablation)ACE · BBH 4 tasks (TSO, DU, PIA, GS)accuracy (%): 49.7 -> 70.1 on PIAImproved
add separate Execute module (ablation)ACE · BBH 4 tasks (TSO, DU, PIA, GS)accuracy (%): 67.4 -> 71.0 on DUImproved
change number of discussion rounds (ablation)PAR, RPD, RTC, TAR baselines · BBH 5 tasksaccuracy (%)Mixed
use GPT-4 instead of GPT-3.5-turbo backboneACE · BBH Tracking Shuffled Objectsaccuracy (%): 37.1 -> 54.2Improved
apply ACE on Llama-2-13B vs baselinesACE · BBH Penguins in a Tableaccuracy (%): 58.4 -> 69.5 (RTC vs ACE)Improved
apply ACE on commonsense recall tasksACE · BBH Hyperbaton / Movie Recommendationaccuracy (%): 77.6 vs 77.0 on Hyperbaton (TAR vs ACE)No clear effect
apply ACE on supplementary datasetsACE · MMLU, StrategyQA, Common MTaccuracy / COMETImproved

Experimental setup

Builds on: multi-agent debate

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