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

• URL: http://arxiv.org/abs/2604.14712v1
• Date: Thu, 16 Apr 2026 07:22:36 GMT
• Title: SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval
• Abstract summary: We introduce textbfSGA-MCTS, a framework that casts LLM planning as non-parametric retrieval.<n>Online, a retrieval-augmented agent employs a hybrid symbolic-semantic mechanism to fetch relevant State-Goal-Action atoms.<n>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.
• Score: 74.1918709002557
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• A Generative Partially Specified Finite State Machine Approach to Complex Behaviour Planning [0.6361348748202732]
  This paper introduces the first GPSFSM framework for robotics, featuring Fabric, an FSM engine that parses, validates, and executes behaviour plans.<n>We release an open-source ROS2 stack that makes generative FSM planning practical and reproducible for robotic systems.
  arXiv  Detail & Related papers  (2026-07-17T06:33:31Z)
• Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap [13.548870367532752]
  Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by responsiveness dependencies.<n>We focus on the task of Generative Stemporal Sequence Recommendation (GSISR), which aims to generate intent sequences that are coherent physically executable within complex contexts.<n>We propose a generative framework, GPlan, that internalizes LLM reasoning into lightweight models through two components.
  arXiv  Detail & Related papers  (2026-05-27T07:27:32Z)
• Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing [15.718757401948304]
  We propose COMLLM, a generative framework that enables foresighted decision-making in MEC systems.<n> COMLLM achieves near-optimal latency and improved load-balancing fairness. Notably, it exhibits zero-shot scalability, allowing a model trained on smallscale networks to generalize to larger, unseen topologies without retraining.
  arXiv  Detail & Related papers  (2026-04-08T14:38:48Z)
• AI4S-SDS: A Neuro-Symbolic Solvent Design System via Sparse MCTS and Differentiable Physics Alignment [0.0]
  We introduce AI4S-SDS, a closed-loop neuro-symbolic framework that integrates multi-agent collaboration with a tailored Monte Carlo Tree Search engine.<n>We show that AI4S-SDS achieves full validity under the adopted HSP-based physical constraints and substantially improves exploration diversity compared to baseline agents.
  arXiv  Detail & Related papers  (2026-03-04T03:30:17Z)
• Agentic Spatio-Temporal Grounding via Collaborative Reasoning [80.83158605034465]
  Temporal Video Grounding aims to retrieve thetemporal tube of a target object or person in a video given a text query.<n>We propose the Agentic Spatio-Temporal Grounder (ASTG) framework for the task of STVG towards an open-world and training-free scenario.<n>Specifically, two specialized agents SRA (Spatial Reasoning Agent) and TRA (Temporal Reasoning Agent) constructed leveraging on modern Multimoal Large Language Models (MLLMs)<n>Experiments on popular benchmarks demonstrate the superiority of the proposed approach where it outperforms existing weakly-supervised and zero-shot approaches by a margin
  arXiv  Detail & Related papers  (2026-02-10T10:16:27Z)
• PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition [49.955269674859004]
  This paper introduces PhyG-MoE (Physics-Guided Mixture-of-Experts), a framework designed to align model capacity with signal complexity.<n>Unlike static architectures, the proposed system employs a spectrum-based gating mechanism that routes signals based on their spectral feature entanglement.<n>A high-capacity TransNeXt expert is activated on-demand to disentangle complex features in saturated scenarios, while lightweight experts handle fundamental signals to minimize latency.
  arXiv  Detail & Related papers  (2026-01-19T07:57:52Z)
• SIGMA: Scalable Spectral Insights for LLM Collapse [51.863164847253366]
  We introduce SIGMA (Spectral Inequalities for Gram Matrix Analysis), a unified framework for model collapse.<n>By utilizing benchmarks that deriving and deterministic bounds on the matrix's spectrum, SIGMA provides a mathematically grounded metric to track the contraction of the representation space.<n>We demonstrate that SIGMA effectively captures the transition towards states, offering both theoretical insights into the mechanics of collapse.
  arXiv  Detail & Related papers  (2026-01-06T19:47:11Z)
• SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot [8.080568103779893]
  State-space language models such as Mamba match Transformer quality while permitting linear complexity inference.<n>Existing one-shot pruning methods are tailored to attention blocks and fail to account for the time-shared and discretized state-transition matrix.<n>We introduce SparseSSM, the first training-free pruning framework that extends the classic optimal brain surgeon (OBS) framework to state space architectures.
  arXiv  Detail & Related papers  (2025-06-11T11:14:57Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• Continuous Monte Carlo Graph Search [61.11769232283621]
  Continuous Monte Carlo Graph Search ( CMCGS) is an extension of Monte Carlo Tree Search (MCTS) to online planning. CMCGS takes advantage of the insight that, during planning, sharing the same action policy between several states can yield high performance. It can be scaled up through parallelization, and it outperforms the Cross-Entropy Method (CEM) in continuous control with learned dynamics models.
  arXiv  Detail & Related papers  (2022-10-04T07:34:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.