Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging
Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead
1
Memory as Plans: World-Action Modeling with Memory-Grounded Planning
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
1
The /wayfinder Skill: Navigating the “Fog of War” of Planning
6 min