Ensuring artificial intelligence behaves in such a way that is aligned with human values is commonly referred to as the alignment challenge. Prior work has shown that rational agents, behaving in such a way that maximizes a utility function, will inevitably behave in such a way that is not aligned with human values, especially as their level of intelligence goes up. Prior work has also shown that there is no "one true utility function"; solutions must include a more holistic approach to alignment. This paper describes oblivious agents: agents that are architected in such a way that their effective utility function is an aggregation of a known and hidden sub-functions. The hidden component, to be maximized, is internally implemented as a black box, preventing the agent from examining it. The known component, to be minimized, is knowledge of the hidden sub-function. Architectural constraints further influence how agent actions can evolve its internal environment model. We show that an oblivious agent, behaving rationally, constructs an internal approximation of designers' intentions (i.e., infers alignment), and, as a consequence of its architecture and effective utility function, behaves in such a way that maximizes alignment; i.e., maximizing the approximated intention function. We show that, paradoxically, it does this for whatever utility function is used as the hidden component and, in contrast with extant techniques, chances of alignment actually improve as agent intelligence grows.
WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
East China Normal University(华东师范大学);Fudan University(复旦大学);Shanghai Innovation Institute(上海创新研究院);Renmin University of China(中国人民大学);Shanghai Qiji Zhifeng Co., Ltd(上海齐治智峰有限公司)
Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
Hugging Face;Ecole Centrale de Lyon(里昂中央理工学院);CNRS(法国国家科学研究中心);Universite Claude Bernard Lyon 1(里昂第一大学(克洛德·贝尔纳));INSA Lyon(里昂国立应用科学学院);Université Lumière Lyon 2(里昂第二大学(卢米埃尔));Inria(法国国家信息与自动化研究所);University of Bordeaux(波尔多大学)
AI Simulations Grounded in Rich Self-Reports Increase Accuracy and Reduce Distortion
Computer Science Department, Stanford University(斯坦福大学计算机科学系);Department of Communication Studies, Northwestern University(西北大学传播学系);Department of Communication, University of Washington(华盛顿大学传播学系);Google DeepMind(谷歌DeepMind);Department of Sociology, Stanford University(斯坦福大学社会学系);Sciences Po(巴黎政治学院)
SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing
Department of Electronic Engineering, Tsinghua University(清华大学电子工程系);School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore(南洋理工大学电子与电气工程学院);MARS Lab, Nanyang Technological University, Singapore(南洋理工大学MARS实验室)
GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Support
Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)(莫扎德人工智能大学);University of Missouri(密苏里大学);Australian National University(澳大利亚国立大学);Linköping University(林肯大学)
ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University(北京航空航天大学未来区块链与隐私计算高精尖创新中心);Beihang University(北京航空航天大学);School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院);School of Mathematical Sciences, Beihang University(北京航空航天大学数学科学学院);Zhongguancun Laboratory(中关村实验室)
Science Done on a Machine by a Machine: AI Agents in Computational Chemistry
State Key Laboratory of Physical Chemistry of Solid Surfaces(固体表面物理化学国家重点实验室);College of Chemistry(化学学院);Xiamen University(厦门大学);School of Physics, Anhui University(安徽大学物理学院)
General-purpose AI models can generate actionable knowledge on agroecological crop protection
Chrysalis Consulting(Chrysalis咨询公司);Institute for Plant Protection, China Academy of Agricultural Sciences(中国农业科学院植物保护研究所);School of the Environment, University of Queensland(昆士兰大学环境学院)