analiza aiqbench
This arXiv preprint proposes modeling an embodied agent's skills as finite-state machines, with task-progress states, transitions, and state-conditioned guidance, and pairs that with a training loop (StateGRPO) that co-evolves skills and model weights. The reported results are broad claims of effectiveness across embodied tasks, but the abstract gives no benchmarks, baselines, or magnitudes, so the evidence needs checking in the full paper. For readers, the practical question is whether structuring skills as explicit states reduces context length and improves transfer compared with flat skill libraries.
StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill
arXiv:2610.14601v1 Announce Type: new Abstract: In this work, we aim to develop an embodied MLLM agent that understands and solves embodied tasks by learning, abstracting, and reusing transferrable and generalizable behavioral patterns. To this end, we propose StateSkill, a new skill representation for embodied agents, which introduces the concept of "finite-state machines" into skill modeling for effective and efficient skill construction and learning. The core idea of StateSkill is to model embodied interaction experiences as a finite-state machine, where a skill is organized around a set of task-progress states, state transitions, and state-conditioned guidance, enabling embodied agents to dynamically adjust their skills as the task progresses while keeping skill contexts compact and stage-relevant. We further develop StateSkill-Evolve, an experience-driven evolution mechanism that iteratively refines StateSkill through retrospective analysis of new successful and failed state-guided trajectories. Upon this, we introduce StateGRPO, which integrates StateSkill evolution and model optimization via state-conditioned GRPO into a unified iterative learning loop, enabling state-conditioned skills and model capabilities to co-evolve and reinforce each other. Extensive experiments demonstrate the effectiveness of our proposed methods and trained model (i.e., StateSkill-Agent) across various embodied tasks.
Abstract:In this work, we aim to develop an embodied MLLM agent that understands and solves embodied tasks by learning, abstracting, and reusing transferrable and generalizable behavioral patterns. To this end, we propose StateSkill, a new skill representation for embodied agents, which introduces the concept of "finite-state machines" into skill modeling for effective and efficient skill construction and learning. The core idea of StateSkill is to model embodied interaction experiences as a finite-state machine, where a skill is organized around a set of task-progress states, state transitions, and state-conditioned guidance, enabling embodied agents to dynamically adjust their skills as the task progresses while keeping skill contexts compact and stage-relevant. We further develop StateSkill-Evolve, an experience-driven evolution mechanism that iteratively refines StateSkill through retrospective analysis of new successful and failed state-guided trajectories. Upon this, we introduce StateGRPO, which integrates StateSkill evolution and model optimization via state-conditioned GRPO into a unified iterative learning loop, enabling state-conditioned skills and model capabilities to co-evolve and reinforce each other. Extensive experiments demonstrate the effectiveness of our proposed methods and trained model (i.e., StateSkill-Agent) across various embodied tasks.
Robotics (cs.RO)
arXiv:2610.14601 [cs.RO]
(or arXiv:2610.14601v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.14601 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 274 cuvinte
Subiecte conexe
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
ContactExplorer: Contact Coverage-Guided Exploration for General-Purpose Dexterous Manipulation
arXiv · 30 sept. 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · 18 sept. 2026
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · 14 sept. 2026