Reinforcement learning for embodied control remains constrained by the difficulty of reward specification. Although recent large language model (LLM)-based methods can synthesize reward functions from natural-language descriptions, they often fail to capture subtle behavioral properties that humans care about, such as...
Eren Sadikoglu, Aditya Taparia, Xin-Yuan Liu et al.· 0 citations
This work introduces SHIFT, which moves execution out of the per-query search loop and shows that choosing structure, instructions, and tools jointly beats choosing only instructions or only tools by up to 9.1 percentage points, and that learned value selection identifies more accurate harnesses with lower execution co...
Som Sagar, Sha-Sha Li, He-Jie Cui et al.· 0 citations
This work introduces PhysicsLENS, a dataset and benchmark for evaluating plausibility of physical properties grounded in robotics, and shows that plausible-looking videos often ignore the stated property, and that stating the property lowers plausibility only slightly and not significantly.
Isaiah Milkey, Som Sagar, Aditya Taparia et al.· 0 citations
This paper introduces Physical Agentic AI, a framework for skill-grounded robot agent orchestration, in which each robot exposes a typed library of executable skills while a foundation model planner decomposes a task into phases and assigns each phase to a robot-skill pair.
Xin-Yuan Liu, Eren Sadikoglu, R. Chatterjee et al.· 0 citations
ARC (Agentic Resource&Configuration learner), a lightweight hierarchical policy that dynamically selects query-specific agent configurations, consistently improves over budget-matched tool-augmented LLMs, demonstrating that learning per-query agent configurations is a powerful alternative to"one size fits all"designs.
Aditya Taparia, Som Sagar, Ransalu Senanayake· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
