Prépublication
· 2026 arXiv
EN
Existing world models typically perceive a scene through current visual frame or a narrow history window. However, these observations may not reveal the physics properties that determine transition dynamics, such as an object's mass distribution, joint damping...
Yunhao Luo, Wentao He et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Multimodal agents (MMAs) sustain interaction through reasoning, memory, tools, and feedback, most visibly as computer-use agents, while robotic systems (RSs) couple sensing and actuation under physical dynamics. We define multimodal embodied agents (MMEAs) as...
Yanzhe Chen, Ziyi Yang et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task-relevant information before acting effectively. Learning such information-gathering behaviors tabula rasa via online reinforcement learning is...
Sriyash Poddar, Yanda Bao et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Vision-language-action (VLA) models have shown promise in robotic manipulation, but imitation learning (IL) alone often struggles to master complex long-horizon skills. Reinforcement learning (RL) offers an effective avenue for further improving VLA policies....
Likui Zhang, Zhe Zhu et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Motivated by the human ability to integrate experience across language, perception, and action, we introduce UniWALM, a unified world-action-language model that learns video, action, and language in a single shared representation, where each modality is both a...
Rahul Sajnani, Diego Romeres et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs. For example, explaining recurring aisle blockages can require re...
Jad Yammine, Malek Wahidi et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult. Reconstructing scenes from single images is a promising alternative, but visual similarity alone is insufficient: objects must also be recover...
Rundong Luo, Yunong Liu et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Reinforcement learning enables mobile robots to make fast and scalable navigation decisions in constrained human-shared environments. However, directly extending single-robot approaches to multi-robot settings often fails to ensure safety and efficiency, espec...
Zehao Wang, Jianpeng Yao et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a five-axis metric: First-Attempt Performance, Efficiency, Succ...
Zekai Li, Jiayi Yu et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality. While general robotic manipulation has been extensively studied, personalized robotic manipulation (PeRM) lacks a controlled benchm...
Zhixu Li, Keqian Tang et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitly specified, from physical properties such as friction and mass to human-defined...
Chenyuan Zhou, Yining Hong et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environments that address a policy's failures and supervision that helps it overcome them...
Tianjiao Yu, Zhilin Ou et al.
#cs.RO