Multi-Agent LLM Systems

LLM: Large Language Model

Multi-agent large language model systems study how multiple language-model agents can divide work, share information, and combine decisions on tasks such as reasoning, coding, research, and planning. Common designs use specialized roles, debate or review loops, retrieval-augmented generation, shared memory, and orchestrators that route tasks or choose communication links; some systems also learn prompts, workflows, or policies through reinforcement learning. Researchers evaluate these approaches on benchmarks for math, question answering, software, and tool use, as well as in longer-running simulations and domain applications. A central open tension is that collaboration can improve accuracy and verification, but may also add latency and token costs or spread errors, bias, and unsafe instructions, so gains depend on the task, architecture, and quality of coordination.

Latest papers

1,050 papers142 papers in the last four weeks, up 35% on the four weeks before. 0.8% of all new papers.

MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability
Jan 14, 2026Handi Chen, Running Zhao, Xiuzhe Wu +2Multi-Agent LLM Systems Multi-Agent Coordination
The University of Hong Kong
StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management
Jan 9, 2026Ruizhe Zhang, Xinke Jiang, Zhibang Yang +12Multi-Agent LLM Systems Multi-Agent Collaboration
School of Computer Science, Peking University, Beijing, China · 2National Engineering Research Center for Software Engineering, Peking University, Beijing, China · 3Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +5
An Agentic AI System for Multi-Framework Communication Coding
Dec 9, 2025Bohao Yang, Rui Yang, Joshua M. Biro +14Healthcare Clinical Information Extraction
Department of Biostatistics and Bioinformatics, Duke School of Medicine, Durham, NC, USA · Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore · Medstar Health National Center for Human Factors in Healthcare, Washington, DC, USA +5
MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS
Nov 28, 2025Kaixiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov +8Multi-Agent LLM Systems LLM Auditing
Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240, China
MASTEST: A LLM-Based Multi-Agent System For Testing RESTful APIs
Nov 22, 2025Xiaoke Han, Hong ZhuMulti-Agent LLM Systems Automated Software Testing
School of Engineering, Computing and Mathematics, Oxford Brookes University, Oxford, UK
Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident Response
Nov 19, 2025Philip DrammehMulti-Agent LLM Systems LLM Agent Orchestration
Independent Researcher
Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning
Nov 14, 2025Dayong Liang, Xiao-Yong Wei, Linhui Xiao +1Multi-Agent LLM Systems Multimodal Reasoning
School of Future Technology, South China University of Technology, Guangzhou, China · Department of networked intelligence, Peng Cheng Laboratory, Shenzhen, China · College of Computer Science, Sichuan University, Chengdu, China +1
Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents
Nov 11, 2025Chih-Hsuan, Yang, Tanwi Mallick +5Multi-Agent LLM Systems Cooperative Game Theory
Bella · Argonne National Laboratory · & University of Chicago
Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry
Oct 29, 2025Run Peng, Ziqiao Ma, Amy Pang +5Multi-Agent LLM Systems LLM Agent Verification
University of Michigan · UNC, Chapel Hill · Georgia Tech +2
MASPRM: Multi-Agent System Process Reward Model
Oct 28, 2025Milad Yazdani, Mahdi Mostajabdaveh, Zirui Zhou +1Multi-Agent LLM Systems Inference-Time Search
Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC V6T1Z4, Canada · Huawei Technologies Canada, Burnaby, BC V5C6S7, Canada
Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy
Oct 2, 2025Meir H. Shachar, Dane M. Sterbentz, Harshitha Menon +10Multiphysics Simulation Multi-Agent LLM Systems
Lawrence Livermore National Laboratory Livermore, CA, USA · Lawrence Livermore National Laboratory Livermore, CA 94550, USA · Sandia National Laboratories Albuquerque, NM, USA +3
MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
Sep 30, 2025Mingjin Li, Yu Liu, Huayi Liu +4Multi-Agent LLM Systems Synthetic Data Generation
Baidu Inc., Beijing, China
Generalized Multi-agent Social Simulation Framework
Sep 26, 2025Gang Li, Jie Lin, Yining Tang +6Multi-Agent LLM Systems Large Language Model-Based Social Simulation
Zhejiang University, China
LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
Aug 25, 2025Bingxi Zhao, Lin Geng Foo, Ping Hu +3Multi-Agent LLM Systems LLM Agents
Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning
Aug 12, 2025Dayu Wang, Yutong Liu, Jiaye Yang +3Multi-Agent LLM Systems Multi-Agent Systems
Baidu Inc. · Peking University
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
Aug 6, 2025Jun Liu, Zhenglun Kong, Changdi Yang +12LLM Context Management Multi-Agent LLM Systems
Carnegie Mellon University · Northeastern University · Harvard University +5
ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism
Aug 1, 2025Rui Sun, Li Zhao, Zuoyou Jiang +5Multi-Agent LLM Systems LLM Agent Orchestration
1Stepfun · 2FinStep
MASCA: LLM based-Multi Agents System for Credit Assessment
Jul 30, 2025Gautam Jajoo, Atharva Pandey, Pranjal A Chitale +1Financial Services Multi-Agent LLM Systems
Kairosity · Microsoft Research · Independent Author
DrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree Search
Jul 10, 2025Zerui Yang, Yuwei Wan, Siyu Yan +3Drug Discovery Agentic RAG
City University of Hong Kong, Hong Kong, PR China · City University of Hong Kong Shenzhen Research Institute, Shenzhen, PR China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou PR China +1
SheetMind: Actions Set Accuracy, Agents Set the Failure Mode
Jun 14, 2025Lyuhao Chen, Xi Cheng, Yanming Kang +11Multi-Agent LLM Systems LLM Agent Evaluation
Carnegie Mellon University · Cornell University · University of California, Berkeley +2
Seven Security Challenges in Cross-domain Multi-agent LLM Systems
May 28, 2025Ronny Ko, Jiseong Jeong, Shuyuan Zheng +4Multi-Agent LLM Systems LLM Agent Security
Osaka University · Seoul National University · Yonsei University
Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning
May 20, 2025Ruiyi Yang, Hao Xue, Imran Razzak +3Multi-Hop QA Multi-Agent LLM Systems
University of New South Wales Sydney, NSW, Australia · Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi, UAE · Griffith University Queensland, Australia +1
Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems
May 19, 2025Ke Chen, Xucheng Yu, Yufei Zhou +1LLM Prompting Automatic Prompt Optimization
School of Information Sciences, University of Illinois Urbana-Champaign, Urbana, USA · Department of Economics, Duke University, Durham, USA
MARFT: Multi-Agent Reinforcement Fine-Tuning
Apr 21, 2025Junwei Liao, Muning Wen, Jun Wang +1Multi-Agent LLM Systems RL Fine-Tuning
Shanghai Jiao Tong University · Shanghai Innovation Institute · OPPO Research Institute
AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations
Apr 13, 2025Jenny Ma, Riya Sahni, Karthik Sreedhar +1Multi-Agent LLM Systems Human Behavior Simulation
Columbia University New York City, USA
Accelerating scientific discovery with Co-Scientist
Feb 26, 2025Juraj Gottweis, Wei-Hung Weng, Alexander Daryin +48Multi-Agent LLM Systems Scientific Hypothesis Generation
Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents
Feb 6, 2025Selim Furkan Tekin, Gaowen Liu, Ramana Rao Kompella +1Multi-Agent LLM Systems Language Model Ensembles
Georgia Institute of Technology · Cisco Systems
DrugAgent: Reliable Multi-Agent Integration of Conflicting Biomedical Evidence for Drug-Target Interaction Assessment
Aug 23, 2024Yoshitaka Inoue, Tianci Song, Xinling Wang +3Multi-Agent LLM Systems LLM Agent Reliability
Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA · Computational Biology Branch, National Library of Medicine, Bethesda, MD, USA · Khoury College of Computer Sciences, Northeastern University, Arlington, VA, USA +2
When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments
Jul 15, 2024Chong Zhang, Xinyi Liu, Zhongmou Zhang +10Multi-Agent LLM Systems Human Behavior Simulation
University of Liverpool, UK · Peking University, China · Shanghai University of Finance and Economics, China +6
Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory
Jun 20, 2024Gordon Dai, Weijia Zhang, Jinhan Li +5Large Language Model-Based Social Simulation Multi-Agent LLM Systems
New York Univeristy, New York, New York, USA · University of illinois at Urbana-Champaign, Urnana, llinois, USA · New York University, New York, New York, USA +1

Jan 14, 2026J/K move · Enter open · S save

MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability

Handi Chen, Running Zhao, Xiuzhe Wu, Zhanfeng Xu+1

The University of Hong Kong

Multi-Agent LLM Systems Multi-Agent Coordination Multi-Agent Reasoning Long-Horizon Agent Tasks

Open paper AskPDF arXiv

Large Language Model (LLM) agents deployed in complex real-world scenarios increasingly operate as spatially distributed entities. However, this physical dispersion constrains agents to limited local perception and finite temporal horizons. We characterize this bottleneck as spatiotemporal partial observability, where spatial and temporal limitations are fundamentally coupled: resolving spatial conflicts requires temporal reasoning about neighbors' future actions, while temporal planning requires spatial context beyond local perception. To bridge this gap, we introduce MACRO-LLM, LLM-empowered multi-agent collaborative reasoning under spatiotemporal partial observability. The architecture interleaves spatial and temporal reasoning within each decision cycle via three interdependent modules: (1) the CoProposer mitigates temporal uncertainty by verifying candidate actions via predictive rollouts; (2) the Negotiator overcomes spatial myopia by resolving conflicts through mean-field statistical aggregation, grounded in the CoProposer's rollout rewards; and (3) the Introspector closes the reasoning loop by analyzing environmental drift and attributing performance changes to refine strategies. Extensive evaluations on two complex long-horizon tasks, cooperative platoon planning and pandemic control, demonstrate that our framework enables robust coordination under spatiotemporal partial observability.