Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Agentic Reinforcement Learning
Paper
•
2602.04284
•
Published
•
13
Didi Chuxing
company
Verified
AI & ML interests
Computer Vision, ASR & TTS, NLP
Recent Activity
Papers
Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Agentic Reinforcement Learning
DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents
yasNing
submitted
a
paper
to Daily Papers
10 days ago