SGA-MCTS：通过无训练原子经验检索解耦规划与执行
SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval
AI总结：
SGA-MCTS通过无训练原子经验检索解耦规划与执行，利用MCTS探索解空间并生成SGA原子，结合检索增强机制实现高效推理，使冻结模型在无需微调的情况下达到SOTA系统性能。
摘要：
LLM驱动的系统需要复杂的多步骤决策能力来解决现实任务，但当前规划方法面临推理时间搜索高延迟与监督微调泛化能力有限的权衡。为解决这一限制，我们引入SGA-MCTS框架，将LLM规划视为非参数检索。离线时，利用MCTS探索解空间，并将高保真轨迹转化为状态-目标-动作（SGA）原子。这些原子是去词化的基本单元，将具体实体抽象为符号槽，保留可重用的因果逻辑并丢弃领域特定噪声。在线时，检索增强代理采用混合符号-语义机制获取相关SGA并重新定位到当前上下文作为软推理提示。在复杂基准测试中，该范式使冻结、无权重模型在无需任务特定微调的情况下达到SOTA系统（如GPT-5）的性能。通过有效摊薄搜索的高计算成本，SGA-MCTS在系统2推理深度上实现了系统1推理速度，使自主规划既可扩展又具备实时可行性。
英文摘要：
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 introduce \textbf{SGA-MCTS}, a framework that casts LLM planning as non-parametric retrieval. Offline, we leverage Monte Carlo Tree Search (MCTS) to explore the solution space and distill high-fidelity trajectories into State-Goal-Action (SGA) atoms. These atoms are de-lexicalized primitives that abstract concrete entities into symbolic slots, preserving reusable causal logic while discarding domain-specific noise. Online, a retrieval-augmented agent employs a hybrid symbolic-semantic mechanism to fetch relevant SGAs and re-ground them into the current context as soft reasoning hints. Empirical results on complex benchmarks demonstrate that this paradigm enables frozen, open-weights models to match the performance of SOTA systems (e.g., GPT-5) without task-specific fine-tuning. By effectively amortizing the heavy computational cost of search, SGA-MCTS achieves System 2 reasoning depth at System 1 inference speeds, rendering autonomous planning both scalable and real-time feasible.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
