AI RESEARCH
Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
arXiv CS.AI
•
ArXi:2602.04284v2 Announce Type: replace Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent efficiency. However, existing studies treat the entire interaction trajectories equally, overlooking the thought necessity and observation utility varies across turns. To this end, we first conduct quantitative investigations into how thought and observation affect agent effectiveness and efficiency. Based on our findings, we propose Agent-Omit, a unified