Related papers: EmbodiSkill: Skill-Aware Reflection for Self-Evolv…
Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through…
Embodied decision-making enables agents to translate high-level goals into executable actions through continuous interactions within the physical world, forming a cornerstone of general-purpose embodied intelligence. Large language models…
Embodied Artificial Intelligence (AI) is an intelligent system formed by agents and their environment through active perception, embodied cognition, and action interaction. Existing embodied AI remains confined to human-crafted setting, in…
The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection. However, this scaling capability remains severely bottlenecked by a…
Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a…
The realization of Artificial General Intelligence (AGI) necessitates Embodied AI agents capable of robust spatial perception, effective task planning, and adaptive execution in physical environments. However, current large language models…
Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental…
Embodied manipulation is a fundamental ability in the realm of embodied artificial intelligence. Although current embodied manipulation models show certain generalizations in specific settings, they struggle in new environments and tasks…
Recent advances in vision-language models (VLMs) have shown promise for human-level embodied intelligence. However, existing benchmarks for VLM-driven embodied agents often rely on high-level commands or discretized action spaces, which are…
The increase in available computing power and the Deep Learning revolution have allowed the exploration of new topics and frontiers in Artificial Intelligence research. A new field called Embodied Artificial Intelligence, which places at…
Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once granted execution authority, the central challenge becomes how to keep actions governable at…
Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.…
Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable…
Humans, even at a very early age, can learn visual concepts and understand geometry and layout through active interaction with the environment, and generalize their compositions to complete tasks described by natural languages in novel…
Achieving general-purpose robotics requires empowering robots to adapt and evolve based on their environment and feedback. Traditional methods face limitations such as extensive training requirements, difficulties in cross-task…
Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based…
Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantially increases the engineering overhead and development time…
Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a…
Most agents today ``self-evolve'' by following rewards and rules defined by humans. However, this process remains fundamentally dependent on external supervision; without human guidance, the evolution stops. In this work, we train agents to…
Learning manipulation skills from human demonstration videos presents a promising yet challenging problem, primarily due to the significant embodiment gap between human body and robot manipulators. Existing methods rely on paired datasets…