While scaling individual Large Language Models (LLMs) has delivered remarkable progress, the next frontier lies in scaling collaboration through multi-agent systems (MAS). However, purely autonomous MAS remain ''closed-world'' systems, constrained by the static knowledge horizon of pre-trained models. This limitation makes them brittle on tasks requiring knowledge beyond training data, often leading to collective failure under novel challenges. To address this, we propose the Human-In-the-Loop Multi-Agent Collaboration (HILA) framework, a principled paradigm for human--agent collaboration. HILA trains agents to learn a metacognitive policy that governs when to solve problems autonomously and when to defer to a human expert. To operationalize this policy, we introduce Dual-Loop Policy Optimization, which disentangles immediate decision-making from long-term capability growth. The inner loop applies Group Relative Policy Optimization (GRPO) with a cost-aware reward to optimize deferral decisions, while the outer loop implements continual learning, transforming expert feedback into high-quality supervised signals that strengthen the agent's reasoning ability. Experiments on challenging mathematical and problem-solving benchmarks show that HILA, equipped with Dual-Loop Policy Optimization, consistently outperforms advanced MAS, establishing a principled foundation for collaborative and continually improving agentic systems.
Autonomous Multi-Agent AI for High-Throughput Polymer Informatics: From Property Prediction to Generative Design Across Synthetic and Bio-Polymers
Institute of Biomedical Engineering University of Oxford(生物医学工程研究所牛津大学);Department of Mechanical and Aerospace Engineering University of Missouri–Columbia(机械与航空航天工程系密苏里大学-哥伦比亚分校);Center for Engineering, Modeling and Applied Social Sciences Federal University of ABC (UFABC)(工程、建模与应用社会科学中心巴西联邦大学ABC分校)
Continual Learning for Peer-to-Peer Federated Learning: A Study on Automated Brain Metastasis Identification
University Hospital Erlangen(埃尔朗根大学医院);Friedrich-Alexander-Universität Erlangen-Nürnberg(埃尔朗根-纽伦堡弗里德里希-亚历山大大学);Comprehensive Cancer Center Erlangen-EMN(埃尔朗根-EMN综合癌症中心)
OEMA: Ontology-Enhanced Multi-Agent Collaboration Framework for Zero-Shot Clinical Named Entity Recognition
Department of Artificial Intelligence, Beijing Key Lab of Traffic Data Analysis;Mining , School of Computer Science \& Technology, Beijing Jiaotong University , Beijing , 100044 , China
Bidirectional human-AI collaboration in brain tumour assessments improves both expert human and AI agent performance
University College London(伦敦大学学院);National Hospital for Neurology and Neurosurgery(国立神经病学和神经外科医院);NVIDIA(英伟达);Great Ormond Street Hospital for Children(大奥蒙德街儿童医院);Royal National Orthopaedic Hospital(皇家国立骨科医院);University College Hospitals NHS Foundation Trust(伦敦大学学院医院国民保健服务基金会信托);Royal Free Hospital(皇家自由医院);Imperial College Healthcare NHS Trust(帝国理工学院医疗保健国民保健服务信托);Imperial College London(帝国理工学院)
CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
The Chinese University of Hong Kong(香港中文大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Georgia(佐治亚大学);National University of Singapore(新加坡国立大学);Dalian University of Technology(大连理工大学);University of Oxford(牛津大学);University of California San Diego(加利福尼亚大学圣迭戈分校);Shenzhen Loop Area Institute(深圳河套学院)
LLMs Can Evolve Continually on Modality for X-Modal Reasoning
Dalian University of Technology(大连理工大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);Tsinghua University(清华大学);The Hong Kong University of Science and Technology(香港科技大学)
ROSClaw: A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration
Shanghai Research Institute for Intelligent Autonomous Systems(上海智能自主系统研究院);National Key Laboratory of Autonomous Intelligent Unmanned Systems (Tongji University)(自主智能无人系统全国重点实验室(同济大学));Frontiers Science Center for Intelligent Autonomous Systems(智能自主系统前沿科学中心);Tongji University(同济大学);College of Electronics and Information Engineering, Tongji University(同济大学电子与信息工程学院)