Tag
This paper introduces adaptive probabilistic shielding for safe reinforcement learning, where the shield is computed from an online learned MDP model, adapting as the model becomes more accurate.
Shilong Liu proposes a taxonomy classifying self-evolving agents into artifact optimization, harness self-improvement, and model learning, providing a common language for emerging agent research.
Observer notes how a model progresses from solving easy tasks with Python to using subcalls for harder tasks over time.