EP197: Teaching AI Agents to Plan Like Humans

Title: From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM AgentsSource: http://arxiv.org/abs/2604.23194v1Summary:This paper introduces AdaPlan-H, a novel agentic reasoning framework that enables LLM agents to dynamically adjust planning granularity based on task complexity. It provides a foundational primitive for long-horizon task execution by mimicking human progressive refinement to optimize the balance between planning detail and execution efficiency.