Multi-Agent Communication Topology

Follow this topic Ask about this topic

Latest papers

41 papers10 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

Illusion: Safeguarding Topology Confidentiality in LLM Multi-Agent Systems via Behavior-Preserving Obfuscation
Oct 31, 2026Yiu-Fai Cheung, Hongzhi Guo, Miao Pan +2Multi-Agent System Security Multi-Agent Communication Topology
The Chinese University of Hong Kong · University of Nebraska-Lincoln · University of Houston +1
Locating and Closing Information Gaps in Multi-Agent Systems
Oct 29, 2026Yaxin Gong, Chongming Gao, Gangyi Zhang +7LLM Agent Workflow Optimization Multi-Agent Systems
University of Science and Technology of China · Qwen Business Unit of Alibaba · National University of Singapore
Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web
Oct 28, 2026Yuqi Qiu, Zuyao Xu, Lu Sun +5Agent Communication Protocols Multi-Agent Communication
Nankai University Tianjin, China · Tsinghua University Beijing, China · Quancheng Laboratory Jinan, China
Test-Time Communication in Trading Agent Swarms
Oct 27, 2026Avid Fayaz, Harry Zhang, Håvard Alstadheim +3Multi-Agent Communication Multi-Agent Systems
Infinite Ascent, Stockholm, Sweden
6G Reasoning Agent Societies: Composition, Scaling, and Consistency-Time Laws
Oct 25, 2026Hatim Chergui, Carolina Fernández-Martínez, Mustapha Benjillali +2Behavioral Consistency of LLM Agents Multi-Agent Communication Topology
i2CAT Foundation, Spain · INPT, Morocco · University of Oulu, Finland +1
Network Topology Does Not Matter: The Breakdown of Classical Consensus in LLM Populations
Oct 24, 2026Sahil Rajesh DhayalkarMulti-Agent Consensus Belief Updating in LLMs
Arizona State University
Network topology shapes consensus and vulnerability in LLM populations
Oct 22, 2026Roberto Passaro, Ariel Flint, Romualdo Pastor-Satorras +2Multi-Agent Consensus Multi-Agent Communication Topology
IT University of Copenhagen, Denmark. · Pioneer Centre for AI, Copenhagen, Denmark. · Department of Mathematics, City St George’s, University of London, UK. +1
Learning Who Talks to Whom: Role-Aware Communication Topology Scheduling for Efficient LLM Multi-Agent Collaboration
Oct 19, 2026Haibin Li, Wenya Yu, Xuefeng Jiang +4Multi-Agent Communication Topology Multi-Agent LLMs
Beihang University · Nanyang Technological University · University of Chinese Academy of Sciences
OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains
Oct 12, 2026Xunkai Li, Miao Zhang, Zekai Chen +6Multi-Agent LLM Systems Multi-Agent Systems
Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures
Oct 7, 2026Xinwen Liu, Zhuocheng Pan, Isabella Zhu +3Agent Failure Analysis Multi-Agent Communication Topology
Beihang University Beijing, China
Collective Regimes in Multi-Agent LLMs under Reasoning Effort and Communication Topology
Sep 27, 2026Machiko Hirota, Akshara Nadayanur Sathis Kanna, Ujwal Kumar +1Multi-Agent LLM Systems Multi-Agent Coordination
University of Pennsylvania · Carnegie Mellon University · Shibaura Institute of Technology
Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate
Sep 22, 2026Boxuan Wang, Zhuoyun Li, Xiaowei Huang +1Multi-Agent Debate Multi-Agent Communication Topology
School of Computer Science and Informatics, University of Liverpool, United Kingdom
Proxifield: Decentralized Multi-Agent Communication through Semantic Proximity
Sep 16, 2026Pradyumna Tambwekar, Yenchia Feng, Deep Patel +1Multi-Agent LLM Systems Multi-Agent Coordination
Distyl AI
BusMA: A Bus Communication Substrate for Multi-Agent Systems
Sep 14, 2026Yanwen Peng, Delvin Ce Zhang, Xi Wang +1Multi-Agent LLM Systems Multi-Agent Coordination
Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom
Disentangling Topology and Diversity in Multi-Agent LLMs for Multilingual Low-Resource Emotion Detection
Sep 13, 2026Ulugbek Shernazarov, Charitha Ruwansiri Weerakon Basnayake, Abdelkhaleq El Jarjini +2Multi-Agent LLM Systems Multi-Agent Communication Topology
Télécom SudParis, Institut Polytechnique de Paris, Évry-Courcouronnes, France · Cardiff Metropolitan University, Cardiff, United Kingdom · Aberystwyth University, Aberystwyth, United Kingdom
Learning How Much to Collaborate: Difficulty-Aware Topology Selection for Multi-Agent Code Generation
Sep 12, 2026Yunsong HongMulti-Agent Coding Agentic Code Generation
School of Computer Science, The University of Sydney, Sydney, NSW 2006, Australia
Inference-Time Graph Engineering for Multi-Agent LLM Workflows
Sep 4, 2026Katherine Tieu, Dongqi Fu, Yinglong Xia +3Multi-Agent LLM Systems Multi-Agent Orchestration
Meta · University of Illinois Urbana-Champaign · Work done at Meta
Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design
Aug 20, 2026Poomphob Suwannapichat, Boonyarit Changaival, Caesar Wu +1Multi-Agent Communication Topology Graph Generation
University of Luxembourg, Luxembourg · King Mongkut’s University of Technology Thonburi, Thailand
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
Aug 13, 2026Junzhi Li, Peng He, Qirui Ji +3Multi-Agent LLM Systems Causal Attribution
University of Chinese Academy of Sciences · National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences · Beijing University of Posts and Telecommunications
HELENA:Hierarchical Sparse Coordination over a Union of Complementary Topologies for MAS
Aug 5, 2026Zhifang Mao, Linyao Zheng, Xuhang Shi +1Multi-Agent LLM Systems Multi-Agent Coordination
1XiaoLab · 2Xi’an Jiaotong University · 3Beijing University of Posts and Telecommunications
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
Jul 30, 2026Mao-xun Huang, Jerry Wang, Yi-Cheng Lai +3Multi-Agent LLM Systems Multi-Agent Coordination
Department of Computer Science, Cornell University, United States · Department of Computer Science, University of Illinois Urbana-Champaign, United States · Institute of Information Science, Academia Sinica, Taiwan
Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems
Jul 24, 2026Mojtaba EslamiMulti-Agent System Optimization Cooperative Game Theory
University of Calgary
QueenBee: A Recursively Self-Improving Harness for Communication Topology Design in LLM-Based Multi-Agent Systems
Jun 25, 2026Congjia Tian, Yuhang Yao, Jiaming CuiMulti-Agent LLM Systems Multi-Agent System Optimization
Virginia Tech, Blacksburg, VA · Carnegie Mellon University, Pittsburgh, PA
Artificial collectives of specialists and generalists excel at different tasks
Jun 18, 2026John Meluso, Laurent Hébert-Dufresne, Christoph Riedl +1Multi-Agent Coordination Multi-Agent Collaboration
Cornell University · University of Vermont · Santa Fe Institute +1
Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventions
Jun 2, 2026Aliakbar Mehdizadeh, Martin HilbertAgent Memory Multi-Agent Coordination
Department of Communication University of California, Davis
Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus
Jun 1, 2026Wanshuang Gou, Zihan LiuMulti-Agent LLM Systems Multi-Agent System Optimization
Chengdu University
LLM Consortium for Software Design Refinement: A Controlled Experiment on Multi-Agent Collaboration Topologies
May 31, 2026Nagarjuna Kanamarlapudi, Praveen KSoftware Engineering Software Architecture Design
Fremont, USA
Structured interactions improve distributed coordination beyond model scaling in a real-world multi-robot system
May 28, 2026Junping Wang, Zhizhong Zhang, Yongqiang Tang +5Multi-Robot Systems Multi-Robot Coordination
1*State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, No.95 Zhongguancun East Road, Haidian District, Beijing, 100190, Beijing, China. · School of Artificial Intelligence, University of Chinese Academy of Sciences, No.19(A) Yuquan Road, Shijingshan District, Beijing, 100049, Beijing, China. · 5Liupanshan Laboratory, Ningxia University, No.489, Helanshan West Road, Xixia District, Yingchuan, 750021, Ningxia, China. +2
TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent Systems
May 27, 2026Yi Ding, Zijie Xuan, Haowei Zhou +6Evolutionary Optimization Multi-Agent System Optimization
National Institute of Metrology, China · University of California, Berkeley · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences +5
MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
May 17, 2026Xuefei Wang, Jialu Wang, Fengbo Zhang +6Continual Learning for LLM Agents Multi-Agent LLM Systems
Beihang University · Independent Researcher · Beijing University of Posts and Telecommunications

Oct 31, 2026J/K move · Enter open · S save

Illusion: Safeguarding Topology Confidentiality in LLM Multi-Agent Systems via Behavior-Preserving Obfuscation

Yiu-Fai Cheung, Hongzhi Guo, Miao Pan, Irwin King+1

The Chinese University of Hong Kong · University of Nebraska-Lincoln · University of Houston+1

Multi-Agent System Security Multi-Agent Communication Topology

Open paper AskPDF arXiv

The communication topology of Large Language Model Multi-Agent Systems (LLM-MASs) governs how information propagates among agents and encodes critical domain knowledge and expert workflow design. It is valuable intellectual property and plays a decisive role in system utility and safety, yet remains vulnerable to inference attacks that stealthily reconstruct it from agent outputs. Existing defenses detect or mitigate such attacks but do not proactively conceal the topology itself. We propose Illusion, a proactive topology obfuscation defense for LLM-MAS. Illusion injects fake edges and fake messages to present attackers with a deceptive topology, while selecting low-impact candidates that preserve output-distribution equivalence and task-accuracy non-inferiority. The resulting fake edges are designed to be indistinguishable from genuine messages under black-box observation. Extensive experiments show that Illusion reduces edge-level F1 from over 0.87 to 0.62 and graph similarity from over 0.94 to 0.71. It also largely preserves output distributions and task performance, and its fake edges resist both similarity-based and LLM-judge filtering, even under adaptive pruning.