Long-horizon embodied tasks require LLM agents to iteratively decompose high-level goals, revise plans in response to environmental feedback, and ground leaf-level subgoals into valid executable actions. Recursive context-management methods such as ReCAP improve planning stability through multi-level task decomposition and parent-node refinement, but still repeatedly invoke the LLM at leaf nodes to ground atomic subtasks into exact valid actions.
Driving World Models (DWMs) have recently advanced rapidly with generative models, yet most existing methods mainly focus on conditional scene generation and lack explicit 3D scene understanding, lang...
arXiv:2608. 14397v1 Announce Type: new Abstract: Zahavy [2026] argues that Large Language Models, despite their capabilities in induction and deduction, cannot perform the abductive "Jump" that produced Einstein's equivalence principle, and attributes this limitation to the absence of embodied simulation.
By Paras Balani, Subhrakanta Panda
arXiv:2608. 14407v1 Announce Type: new Abstract: We present a survey of the past and future of AI Scientists: machines capable of automating science.
By Ross D. King
arXiv:2608. 13719v1 Announce Type: new Abstract: Autonomous systems can fail in rare and heterogeneous ways, making real-world failure discovery difficult under limited testing budgets.
By Anjali Parashar, Rachel Luo, Apoorva Sharma, Sushant Veer, Edward Schmerling, Carson Sobolewski, Mingxin Yu, Chuchu Fan, Marco Pavone
arXiv:2608. 14135v1 Announce Type: cross Abstract: Autonomous pursuit-evasion is a fundamental challenge for Unmanned Aerial Vehicles (UAVs), requiring rapid decision-making under tightly coupled dynamics and continuously changing opponent behaviors.
By Wenhao Tang, Tianyang Chen, Zhejun Cui, Boyuan An, Jiayu Chen, Ruize Zhang, Huidong Liu, Tianyue Wu, Qingmin Liao, Fei Gao, Yu Wang, Chao Yu
arXiv:2608. 14498v1 Announce Type: new Abstract: Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions.
By Hanfeng Lu, Tianyu Feng, Suyi Li, Yuheng Zhao, Wei Gao, Shaopan Xiong, Ju Huang, Siran Yang, Jiamang Wang, Lin Qu, Wei Wang
arXiv:2608. 14047v1 Announce Type: cross Abstract: This paper integrates end-to-end Visual-Language-Action (VLA) models with agentic tool-use to propose Agentic Robot with Tool-use (ART).
By Yi Ding, Yanzhao Yu, Xili Dai, Xianbiao Qi, Peiwen Sun, Xueqian Wang, Xiangyu Yue, Jianan Wang
arXiv:2604. 16509v2 Announce Type: replace-cross Abstract: Many robotic exploration algorithms rely on graph structures for frontier-based exploration and dynamic path planning.
By Adithya V. Sastry, Bibek Poudel, Weizi Li
arXiv:2608. 14028v1 Announce Type: cross Abstract: Dexterous manipulation is a fundamental capability for embodied intelligence, but scaling it remains difficult because robot demonstrations are expensive to collect and action spaces vary across embodiments.
By Zhiyue Zhao, Jingyi Wu, Hairuo Liu, Mingyu Liu, Liyang Li, Hengdi Zhang, Tong He, Zhengxue Cheng
arXiv:2608. 13600v1 Announce Type: cross Abstract: We study Evolution Strategies (ES) for continual control, where agents must adapt to changing tasks without forgetting previous ones.
By Nicola Pitzalis, Eleni Nisioti, Antonio Carta, Davide Bacciu, Andrea Cossu
arXiv:2608. 14481v1 Announce Type: cross Abstract: As heterogeneous robotic systems deploy across diverse urban zones, maintaining safety amid complex human-robot interactions remains a critical challenge.
By Alexei Odinokov, Rostislav Yavorskiy
arXiv:2608. 14379v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation.
By Yuxuan Chen, Wanruo Zhang, Xiao Li
arXiv:2608. 13900v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from conversational assistants into autonomous systems that execute long-horizon tasks through reasoning, tool use, code generation, and workspace manipulation.
By Zhaoyan Sun, Xiaoxiao Wang, Guoliang Li
arXiv:2608. 13958v1 Announce Type: new Abstract: How do we govern AI systems whose reasoning we cannot fully inspect?
By James K. Wiles
arXiv:2608. 13684v1 Announce Type: new Abstract: This paper describes a neurosymbolic architecture for learning to assemble novel structures using evidence from embodied conversations and task demonstrations.
By Jonghyuk Park, Alex Lascarides, Subramanian Ramamoorthy
arXiv:2608. 13605v1 Announce Type: new Abstract: Natural language provides robots with a flexible task interface, but target ambiguity in embodied environments arises not only from user intent; it can also result from missing taskrelevant physical evidence in the current observation.
By Yiwei Liu, Luwei Yang
arXiv:2608. 13678v1 Announce Type: cross Abstract: A central goal of robot learning is to enable robots to execute rich instructions specified at runtime.
By Moritz Zoellner, Anastasios Manganaris, Ahmed H. Qureshi, Rohan Paleja
arXiv:2608. 14466v1 Announce Type: cross Abstract: An autonomous robot efficiently exploring an unknown environment, such as looking for water sources on Mars, faces two simultaneous demands: building an accurate information map while quickly finding the regions of greatest value, and paying for every meter of travel and the cost of every measurement it takes.
By Ajith Anil Meera, Pablo Lanillos, Wouter Kouw
arXiv:2507. 02169v2 Announce Type: replace Abstract: Machine learning models are often used in applications where their inputs change due to routine interactions, strategic manipulation, or noise.
By Harry Cheon, Meredith Stewart, Bogdan Kulynych, Tsui-Wei Weng, Berk Ustun