Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks. In open-ended settings, optimizing collaboration for efficiency and effectiveness demands flexible adjustments. Despite this, current research mainly emphasizes fixed, task-oriented workflows and overlooks agent-centric organizational structures. Drawing inspiration from human organizational behavior, we introduce a self-organizing agent system (S-Agents) with a "tree of agents" structure for dynamic workflow, an "hourglass agent architecture" for balancing information priorities, and a "non-obstructive collaboration" method to allow asynchronous task execution among agents. This structure can autonomously coordinate a group of agents, efficiently addressing the challenges of open and dynamic environments without human intervention. Our experiments demonstrate that S-Agents proficiently execute collaborative building tasks and resource collection in the Minecraft environment, validating their effectiveness.
O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering
Zhejiang University(浙江大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Science and Technology of China(中国科学技术大学);Fudan University(复旦大学);State Key Laboratory of Industrial Control Technology(工业控制技术国家重点实验室)
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)
An Evolutionary Agentic Approach for Open-ended Image Quality Perception
New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);The Hong Kong University of Science and Technology(香港科技大学);Transsion(传音)
MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
The Chinese University of Hong Kong(香港中文大学);Zhongshan Hospital, Fudan University(复旦大学附属中山医院);South China University of Technology(华南理工大学);Chinese Academy of Sciences(中国科学院)
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)
When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations
The University of Hong Kong(香港大学);Peking University(北京大学);Tsinghua University(清华大学);Beijing Institute of Mathematical Sciences and Applications (BIMSA)(北京数学科学与应用研究院)
ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
Department of Computer Science(计算机科学系);The University of Texas at Austin(德克萨斯大学奥斯汀分校);College of Computing and Data Science(计算与数据科学学院);Nanyang Technological University(南洋理工大学)
Collaborative Auto-Curricula Multi-Agent Reinforcement Learning with Graph Neural Network Communication Layer for Open-ended Wildfire-Management Resource Distribution
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)
A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Institut des Systèmes Intelligents et de Robotique(智能系统与机器人研究所);INRIA Bordeaux Sud-Ouest(法国国家信息与自动化研究所波尔多南部-西部分部);Institute of Cognitive Sciences and Technologies(认知科学与技术研究所);CNR(意大利国家研究委员会);CITIC(信息与通信技术中心);Universidade da Coruña(拉科鲁尼亚大学);Massachusetts Institute of Technology(麻省理工学院)
Open-Ended Learning Leads to Generally Capable Agents
DeepMind(深度思维)
在这项工作中,我们创建的代理,可以执行远远超出一个单一的,个人的任务,表现出更广泛的行为概括到一个巨大的,丰富的挑战空间。我们定义了一个环境领域内的任务的宇宙,并展示了训练代理,一般能够跨越这个广阔的空间和超越的能力。环境是天生的多智能体,跨越竞争,合作和独立游戏的连续体,这些游戏位于程序生成的物理3D世界中。由此产生的空间是非常多样化的,在对代理人提出的挑战,因此,即使是测量代理人的学习进度是一个开放的研究问题。我们提出了一个迭代的概念,连续几代代理之间的改进,而不是寻求最大化一个单一的目标,使我们能够量化的进展,尽管任务是无与伦比的可实现的奖励。我们表明,通过构建一个开放式的学习过程,动态地改变训练任务分布和训练目标,使代理永远不会停止学习,我们实现了新行为的一致学习。由此产生的智能体能够在我们人类可解决的每一个评估级别中获得奖励,其行为可以推广到任务领域中的许多点。这种zero-shot概括的例子包括在Hide and Seek、Capture the Flag和Tag上的良好性能。通过分析和手工创作的探测任务,我们发现我们的代理人的行为,并发现有趣的新兴启发式行为,如试错实验,简单的工具使用,选项切换和合作。最后,我们证明了这个代理的一般能力可以通过廉价的微调解锁更大规模的行为转移。