Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Agentic Reinforcement Learning
IntermediateYansong Ning, Jun Fang et al.Feb 4arXiv
Agent-Omit teaches AI agents to skip unneeded thinking and old observations, cutting tokens while keeping accuracy high.
#LLM agents#reinforcement learning#agentic RL