This benchmark evaluates continual learning for self-evolving embodied agents.
A new embodied benchmark tests continual learning by requiring agents to recombine basic skills for unseen advanced tasks, revealing limited scaling.
A new embodied benchmark tests continual learning by requiring agents to recombine basic skills for unseen advanced tasks, revealing limited scaling.
Tutorial Agentic Learning lets frozen LLM agents learn from videos via reusable tutorial memories, gap probing, and refinement without retraining.