CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）科学与工程学院）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）人工智能学院）；Tsinghua University（清华大学）；AutoGame Research（AutoGame研究）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
Large language models are enabling language-conditioned agents in interactive environments, but highly cooperative tasks often impose two simultaneous constraints: sub-second real-time coordination and sustained multi-episode adaptation under a strict online token budget. Existing approaches either rely on frequent in-episode reasoning that induces latency and timing jitter, or deliver post-episode improvements through unstructured text that is difficult to compile into reliable low-cost execution. We propose CoWork-X, an active co-evolution framework that casts peer collaboration as a closed-loop optimization problem across episodes, inspired by fast--slow memory separation. CoWork-X instantiates a Skill-Agent that executes via HTN (hierarchical task network)-based skill retrieval from a structured, interpretable, and compositional skill library, and a post-episode Co-Optimizer that performs patch-style skill consolidation with explicit budget constraints and drift regularization. Experiments in challenging Overcooked-AI-like realtime collaboration benchmarks demonstrate that CoWork-X achieves stable, cumulative performance gains while steadily reducing online latency and token usage.
MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration
Queen Mary University of London（伦敦玛丽女王大学）；Duke Kunshan University（昆山杜克大学）；Hong Kong University of Science and Technology（香港科技大学）；School of Engineering, Westlake University（西湖大学工学院）；Research Center for Industries of the Future, Westlake University（西湖大学未来产业研究中心）
CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
Shanghai Institute of AI for Education（上海人工智能教育研究院）；School of Computer Science（计算机科学学院）；East China Normal University（东华大学）；Tencent Inc.（腾讯公司）；Shanghai Innovation Institute（上海创新研究院）
Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration
Northeastern University（东北大学）；University of Notre Dame（Notre Dame 大学）；University of Waterloo（滑铁卢大学）；Carnegie Mellon University（卡内基梅隆大学）；Adobe（Adobe公司）；Microsoft Research Asia（微软亚洲研究院）
Attack and defense techniques in large language models: A survey and new perspectives
School of Computer Engineering, Jimei University, Xiamen, China（集美大学计算机工程学院）；College of Science, Mathematics and Technology, Wenzhou-Kean University, Wenzhou, China（温州市凯恩大学科学、数学与技术学院）；School of Smart Education, Jiangsu Normal University, Xuzhou, China（江苏师范大学智能教育学院）
Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
The Chinese University of Hong Kong（香港中文大学）；LLM Department, Tencent（腾讯语言模型部门）；Mohamed bin Zayed University of Artificial Intelligence（马尔代夫人工智能大学）；McGill University（麦吉尔大学）；City University of Hong Kong（香港城市大学）；The University of Edinburgh（爱丁堡大学）
RTLSquad: Multi-Agent Based Interpretable RTL Design
National University of Defense Technology（国防科技大学）；Intelligent Microelectronics Center（智能微电子中心）；Qiyuan Lab（启元实验室）；Defense Innovation Institute（国防创新研究院）；Academy of Military Science（军事科学院）
