AI RESEARCH

SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval

arXiv CS.AI

ArXi:2604.14712v1 Announce Type: new LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inference-time search and the limited generalization of supervised fine-tuning. To address this limitation, we