AI Paper Atlas

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

MPAS: Breaking Sequential Constraints of Multi-Agent Communication Topologies via Individual-Epistemic Message Propagation

Jingxuan Yu, Ju Jia, Simeng Qin, Xiaojun Jia, Siqi Ma, Yihao Huang, Yali Yuan, Guang Cheng

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: LLM multi-agent decision making · 2 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 MPAS, a multi-agent communication framework that breaks the sequential topological-order constraint of LLM agent graphs via individual-epistemic message propagation.

Problem

Existing LLM multi-agent systems arrange agent communication as a directed acyclic graph executed one-by-one via topological sort, which imposes sequential constraints on agent communication.

Approach

Replaces sequential topological-order execution of agent graphs with individual-epistemic message propagation, letting agents communicate without a strict one-by-one ordering. Details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace sequential execution with node-wise parallel message propagationmulti-agent topology · six benchmarks (handcrafted topologies)accuracy: +0.9% to +6.4%Improved
use MPAS with optimized topology instead of G-Designermulti-agent system · MMLUaccuracy: 76.9 -> 77.3Improved
use MPAS optimized topology instead of Agent-Prunemulti-agent system · HumanEvalaccuracy: 84.9 -> 87.2Improved
use parallel MPAS instead of sequential G-Designer at 11 agentscommunication · AQuAtime per round (s): 84.6 -> 14.2Improved
use MPAS instead of G-Designer with 3 agentscommunication · AQuAtime per round (s): 7.6 vs 7.8No clear effect
use MPAS under backdoor attackmulti-agent system · MMLUaccuracy: GPTSwarm 45.8 -> MPAS 72.1Improved
add attention aggregator (clean) (ablation)MPAS · MMLU, GSM8K, AQuA, HumanEvalaccuracy: 77.3 -> 78.7 (MMLU)Improved
add attention aggregator (clean) (ablation)MPAS · MultiArithaccuracy: 96.7 -> 95.8Hurt
add selective aggregator under backdoor (ablation)MPAS · MMLU backdooraccuracy: 72.5 -> 77.1Improved
add attention aggregator under backdoor (ablation)MPAS · MMLU backdooraccuracy: 72.5 -> 67.2Hurt
add selective aggregator in clean setting (ablation)MPAS · MMLUaccuracy: 77.3 -> 76.6Hurt
increase communication rounds beyond two on small graphs (ablation)MPAS · five-agent cycleperformanceNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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