Multi-Agent LLMs

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 144% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 211

All topics

Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?
Oct 8, 2026Xingwu Zhang, Duanyang Du, Huiling Zhu +5Industrial Anomaly Detection Multimodal Anomaly Detection
Hunan University · University of Aberdeen · South China Normal University +1
From Expert-Guided Proof Search to Automated Open-Problem Solving
Oct 7, 2026Adrián Zámečník, Matěj Kripner, Martin Koutecký +5Automated Theorem Proving AI Agents for Scientific Discovery
Computer Science Institute, Charles University · Institute of Formal and Applied Linguistics, Charles University · Department of Applied Mathematics, Charles University +1
Disentangling Models from Personas in Heterogeneous LLM Simulations
Oct 6, 2026Dani Roytburg, Daphne IppolitoLarge Language Model-Based Social Simulation Multi-Agent LLMs
Carnegie Mellon University
templar: agentic induction and evolution of standardized radiology reporting templates from large-scale clinical corpora
Oct 4, 2026Xiaotian Hu, Mingxuan Liu, Zhonghan Wang +9Radiology Report Generation Multi-Agent LLMs
Tsinghua University · University of Hong Kong · University of California, San Diego
Consensus and Factual Dynamics in Large Populations of Interacting Language Models
Sep 30, 2026Emanuele Ricco, Elia Onofri, Vincenzo Sammartino +1Hallucination in Language Models Multi-Agent Consensus
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST) Thuwal 23955, Saudi Arabia · Dipartimento di Informatica, Universit`a di Pisa Pisa, Italy
From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
Sep 29, 2026Kunal Jha, Max Kleiman-Weiner, Natasha JaquesLLM Agent Self-Improvement LLM Agent Skill Learning
Department of Computer Science, University of Washington, Seattle, WA 98195, USA.
Absorbing State Phase Transitions in Multi-Agent Search
Sep 29, 2026Wenwen Zheng, Yuzhe Yang, Helen Qu +2Phase Transitions Multi-Agent Systems
Flatiron Institute
MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems
Sep 29, 2026Lei Ma, Dennis Hofmann, Haowen Xu +4AI Agent Benchmarks Multi-Agent LLMs
Worcester Polytechnic Institute · University of Arizona
Principled Thoughts for Latent Recursive LLM Systems
Sep 28, 2026Fahd Seddik, Fatemeh FardContinuous Latent Reasoning Multi-Agent LLMs
FARD Lab, University of British Columbia, Okanagan, Canada
LongCat-DeepResearch Technical Report
Sep 28, 2026Meituan LongCat Team, He Zhu, Yue Xu +28Deep Research Agents Multi-Agent Planning
Meituan LongCat Team
Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents
Sep 28, 2026Sidharth Pulipaka, Ansh Sharma, Stanislau Hlebik +4AI Agent Security Agent Memory Poisoning
SPAR · University of Cambridge · APTA AI +1
LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems
Sep 27, 2026Liron Soffer, Ravid Shwartz-Ziv, Chen ShaniNormative Conformity in Language Models Social Bias in Language Models
Tel-Aviv University · New York University
AgenticSizing: A Large Language Model-based Multi-Agent Framework for Analog Circuit Sizing
Sep 22, 2026Yijia Hao, Pratibha Verma, Dongxu Guo +4Large Language Model-Guided Optimization Electronic Design Automation
Centre for Electronics Frontiers, Institute for Integrated Micro and Nano Systems, School of Engineering, The University of Edinburgh, UK · Department of Electrical Engineering, Indian Institute of Technology Indore, India · School of Informatics, The University of Edinburgh, UK +1
Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows
Sep 20, 2026Vivek Kumar Singh, Preeti Priyam, Gautam BhowmickLLM Agent Memory Cost-Aware Inference
Independent Researcher McKinney, TX, USA · Independent Researcher Chicago, IL, USA
Digital Twins for Opinion Dynamics: A Generative LLM Framework for Social Networks
Sep 17, 2026Omran Berjawi, Giuseppe Fenza, Rida Khatoun +1Opinion Dynamics Human Behavior Simulation
Information Processing and Communication Laboratory (LTCI) Institut Polytechnique de Paris, T´el´ecom Paris Palaiseau, France · Management & Information Systems (DISA-MIS) University of Salerno Fisciano, Italy · College of Communication and Information, University of Kentucky +1
Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry
Sep 16, 2026Peter PotashLLM Evaluation Pragmatic Reasoning in Language Models
Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents
Sep 16, 2026Dohun Lee, Hyunwoo ParkAdversarial Attacks on LLMs AI Agent Security
Graduate School of Data Science, Seoul National University
Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric
Sep 16, 2026Omran Berjawi, Giuseppe Fenza, Rida KhatounOpinion Dynamics Social Bias in Language Models
Institut Polytechnique de Paris, Télécom Paris, Palaiseau, France · University of Salerno, Fisciano, Italy
ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM Failures
Sep 15, 2026Muhammad Ashar Ishfaq, Glaucia MeloTheory of Mind LLM Agent Evaluation
The Islamia University of Bahawalpur, Pakistan · Toronto Metropolitan University, Toronto, Canada
Cheap Talk Stabilizes Strategic Interaction in LLM Agents
Sep 14, 2026Nunzio Lorè, Hongan Zhu, Babak HeydariRepeated Games LLM Agents
Multi-Agent Intelligent Complex Systems (MAGICS) Lab, Northeastern University, Boston, MA, USA
Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training
Sep 12, 2026Luming Yang, Haoxian Liu, Siqing Li +4Educational Technology LLM Agent Evaluation
Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA · Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China · Department of Statistics and Data Science, Southern University of Science and Technology, Shenzhen, China +3
A Voice-Interactive Multi-Agent System for Smart Operating Rooms: Architecture Design and Key Technologies
Sep 10, 2026Tianxiang ZhouLanguage Model-Based Control LLM Agent Orchestration
Wuhan United Imaging Surgical Co., Ltd. (UIS) Wuhan, China
Multi-Agent Agentic Graph Learning via Structural Signatures
Sep 10, 2026Liang Qu, Jianxin Li, Hua WangGraph Representation Learning LLM Reasoning with Graphs
Edith Cowan University, Perth, Australia. · Victoria University, Melbourne, Australia.
Scaling Multi-Agent Systems with Prospect-State Propagation
Sep 7, 2026Zhimei Chen, Mu Chen, Fakhri KarrayAgent-Based Modeling Multi-Agent Systems
1Independent Researcher · 2Mohamed bin Zayed University of Artificial Intelligence · University of Waterloo
ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies
Sep 7, 2026Xinran Zhang, Pengrui Lu, Lyumanshan Ye +1AI-Assisted Decision Making LLM Agent Evaluation
1Shanghai Innovation Institute · 2Beijing Institute of Technology · 4GAIR Lab +1
GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions
Sep 1, 2026Elias Stengel-Eskin, Newton Sander, Carlos Bonetti +4Multi-Agent LLMs Emergent Communication
University of Texas at Austin · AE Studio · Schmidt Sciences +1
ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything
Sep 1, 2026Yufan Dang, Shu Yao, Bowen Lai +6Multi-Agent Orchestration Multi-Agent Systems
Tsinghua University · Shanghai Innovation Institute · Shanghai Jiao Tong University +3
Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
Sep 1, 2026Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti +4LLM Agent Orchestration LLM Agent Workflow Optimization
University of Waterloo · Manulife
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
Sep 1, 2026Rui Yang, Junjie Xu, Zhengyu Liu +4AI Agent Security Benchmarks Multi-Agent System Security
Johns Hopkins University · Nanyang Technological University
SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?
Aug 31, 2026Jinshan Gao, Zhuoran Jin, Tianyi Men +2LLM Agent Orchestration AI Agent Benchmarks
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

Oct 8, 2026, cs.CVJ/K move · Enter open · S save

Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?

Xingwu Zhang, Duanyang Du, Huiling Zhu, Jiayue Dai+4

Hunan University · University of Aberdeen · South China Normal University+1

Industrial Anomaly Detection Multimodal Anomaly Detection Anomaly Localization Multi-Agent LLMs

Open paper AskPDF arXiv

A single multimodal large language model (MLLM) struggles to excel simultaneously at detection, localization, description, and reasoning in multimodal industrial anomaly understanding (MM-IAU). We show that in-domain training does not close this gap. On MMAD, a widely adopted MM-IAU benchmark, trained specialists reach at most 75.5% accuracy in defect localization, against 92.3% for human experts, and even detect anomalies less accurately than their untrained base model. Meanwhile, different MLLMs offer complementary strengths but share this weakness in fine-grained perception, so combining them alone cannot remove it. We therefore propose SiGMA, a spatially grounded multi-agent framework that divides labor between heterogeneous MLLM agents and a dedicated visual defect expert. A multimodal searcher supplies industrial knowledge and normal references, the defect expert turns query-reference comparison into calibrated anomaly evidence, and a label-free reliability controller weighs each source by task-wise competence and query-level evidence quality. SiGMA reaches 85.2% average accuracy on MMAD, 4.0% above the strongest trained specialist and Gemini-2.5-Pro and within 1.5% of human experts. Even with three agents of at most 9B parameters, it reaches 84.4%, and new MLLMs join without retraining.

Momentum

Related topics

Latest papers 211