CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
MIT(麻省理工学院);NUS(新加坡国立大学);MiniMax;McGill(麦吉尔大学);Stanford(斯坦福大学);SambaNova;Meta;Singapore-MIT Alliance for Research and Technology(新加坡-麻省理工联合研究技术联盟);Amazon(亚马逊);Microsoft(微软)
Ao Qu, Han Zheng, Zijian Zhou, Yihao Yan, Yihong Tang, Shao Yong Ong, Fenglu Hong, Kaichen Zhou, Chonghe Jiang, Minwei Kong, Jiacheng Zhu, Xuan Jiang, Sirui Li,… 展开作者
Ao Qu, Han Zheng, Zijian Zhou, Yihao Yan, Yihong Tang, Shao Yong Ong, Fenglu Hong, Kaichen Zhou, Chonghe Jiang, Minwei Kong, Jiacheng Zhu, Xuan Jiang, Sirui Li, Cathy Wu, Bryan Kian Hsiang Low, Jinhua Zhao, Paul Pu Liang
Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rules, which limit the autonomy of LLM agents. We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems. CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate through shared persistent memory, asynchronous multi-agent execution, and heartbeat-based interventions. It also provides practical safeguards, including isolated workspaces, evaluator separation, resource management, and agent session and health management. Evaluated on diverse mathematical, algorithmic, and systems optimization tasks, CORAL sets new state-of-the-art results on 10 tasks, achieving 3-10 times higher improvement rates with far fewer evaluations than fixed evolutionary search baselines across tasks. On Anthropic's kernel engineering task, four co-evolving agents improve the best known score from 1363 to 1103 cycles. Mechanistic analyses further show how these gains arise from knowledge reuse and multi-agent exploration and communication. Together, these results suggest that greater agent autonomy and multi-agent evolution can substantially improve open-ended discovery. Code is available at https://github.com/Human-Agent-Society/CORAL.
Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification
University of Science and Technology of China(中国科学技术大学);Institute of Computing Technology, CAS(中国科学院计算技术研究所);Cambricon Technologies(寒武纪科技);Intelligent Software Research Center, Institute of Software, CAS(中国科学院软件研究所智能软件研究中心);University of Chinese Academy of Sciences(中国科学院大学);Shanghai Innovation Center for Processor Technologies(上海处理器技术创新中心)
SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation
Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore(眼科学系,Yong Loo Lin医学院,新加坡国立大学,新加坡);Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, India(计算与数据科学系,印度科学研究院,班加罗尔,卡纳塔克邦,印度)
Autonomous Open-Ended Learning of Tasks with Non-Stationary Interdependencies
Universidade da Coruña(拉科鲁尼亚大学);Consiglio Nazionale delle Ricerche(意大利国家研究委员会);Istituto di Scienze e Tecnologie della Cognizione(认知科学与技术研究所);CITIC research center(CITIC研究中心)
Safety Must Precede the Deployment of Open-Ended AI
CISPA-Helmholtz Center of Information Security(CISPA-海德堡信息安全中心);MPI for Intelligent Systems, ELLIS Institute Tübingen, Tübingen AI Center(智能系统Max Planck研究所、图宾根ELLIS研究所、图宾根人工智能中心)
Operationalizing Serendipity: Multi-Agent AI Workflows for Enhanced Materials Characterization with Theory-in-the-Loop
Physical Sciences Division, Pacific Northwest National Laboratory(太平洋西北国家实验室物理科学部);Computational Sciences and Engineering Division, Oak Ridge National Laboratory(橡树岭国家实验室计算科学与工程部);AtomQ
The Autonomy-Alignment Problem in Open-Ended Learning Robots: Formalising the Purpose Framework
Institute of Cognitive Sciences and Technologies, National Research Council(认知科学与技术研究所,国家研究理事会);Integrated Group for Engineering Research, CITIC, Universidade da Coruña(工程研究联合组,CITIC,科鲁纳大学);Institute of Intelligent Systems and Robotics, Sorbonne University / CNRS(智能系统与机器人研究所,索邦大学 / CNRS)
Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology
Institute of Astronomy, University of Cambridge(剑桥大学天文研究所);Kavli Institute for Cosmology, University of Cambridge(剑桥大学凯斯勒宇宙研究所);Cavendish Astrophysics, University of Cambridge(剑桥大学卡文迪许天体物理研究所)
StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production-Living Simulations with Stardew Valley
Nanyang Technological University(南洋理工大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));East China University of Science and Technology(华东理工大学);Singapore Management University(新加坡管理大学)
Cultural Alien Sampler: Open-ended art generation balancing originality and coherence
Max Planck Institute for Human Development(马克斯·普朗克人类发展研究所);Academy of Media Arts Cologne(科隆媒体艺术学院);Tiptree Systems(蒂普特里系统);NVIDIA(NVIDIA公司);BFM, Tallinn University(BFM,塔林大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
G-Zero: Self-Play for Open-Ended Generation from Zero Data
Washington University in St. Louis(华盛顿大学圣路易斯分校);University of Virginia(弗吉尼亚大学);University of Maryland(马里兰大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)
BIMgent: Towards Autonomous Building Modeling via Computer-use Agents
Chair of Computing in Civil and Building Engineering, Technical University of Munich, Germany(土木与建筑工程计算系,慕尼黑技术大学);TUM Georg Nemetschek Institute, Munich, Germany(慕尼黑技术大学Georg Nemetschek研究所)
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
University of Science and Technology of China(中国科学技术大学);The Chinese University of Hong Kong(香港中文大学);University of Macau(澳门大学);Tsinghua University(清华大学);Zhejiang University(浙江大学);Soochow University(苏州大学);Brown University(布朗大学);Shanghai Jiao Tong University(上海交通大学)