SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search

• URL: http://arxiv.org/abs/2512.23167v1
• Date: Mon, 29 Dec 2025 03:19:42 GMT
• Title: SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search
• Authors: Yifan Zhang, Giridhar Ganapavarapu, Srideepika Jayaraman, Bhavna Agrawal, Dhaval Patel, Achille Fokoue,
• Abstract summary: SPIRAL is a novel framework that embeds a cognitive architecture of three specialized Large Language Models into an Monte Carlo Tree Search loop.<n>On the DailyLifeAPIs and HuggingFace datasets, SPIRAL consistently outperforms the default Chain-of-the-art planning method.<n>Our work demonstrates that structuring LLM reasoning as a guided, reflective, and grounded search process yields more robust and efficient autonomous planners.
• Score: 11.651841902428673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) often falter at complex planning tasks that require exploration and self-correction, as their linear reasoning process struggles to recover from early mistakes. While search algorithms like Monte Carlo Tree Search (MCTS) can explore alternatives, they are often ineffective when guided by sparse rewards and fail to leverage the rich semantic capabilities of LLMs. We introduce SPIRAL (Symbolic LLM Planning via Grounded and Reflective Search), a novel framework that embeds a cognitive architecture of three specialized LLM agents into an MCTS loop. SPIRAL's key contribution is its integrated planning pipeline where a Planner proposes creative next steps, a Simulator grounds the search by predicting realistic outcomes, and a Critic provides dense reward signals through reflection. This synergy transforms MCTS from a brute-force search into a guided, self-correcting reasoning process. On the DailyLifeAPIs and HuggingFace datasets, SPIRAL consistently outperforms the default Chain-of-Thought planning method and other state-of-the-art agents. More importantly, it substantially surpasses other state-of-the-art agents; for example, SPIRAL achieves 83.6% overall accuracy on DailyLifeAPIs, an improvement of over 16 percentage points against the next-best search framework, while also demonstrating superior token efficiency. Our work demonstrates that structuring LLM reasoning as a guided, reflective, and grounded search process yields more robust and efficient autonomous planners. The source code, full appendices, and all experimental data are available for reproducibility at the official project repository.

Related papers

• ReflecSched: Solving Dynamic Flexible Job-Shop Scheduling via LLM-Powered Hierarchical Reflection [4.101501114944147]
  ReflecSched is a framework that empowers the LLM beyond a direct scheduler.<n>It distills simulations across multiple planning horizons into a concise, natural-language summary.<n>This summary is then integrated into the prompt of a final decision-making module, guiding it to produce non-myopic actions.
  arXiv  Detail & Related papers  (2025-08-03T11:26:35Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition [5.5688696788198975]
  We introduce SELT (Self-Evaluation LLM Tree Search), a novel framework to enhance LLM reasoning without relying on external reward models.<n>We validate our approach on challenging benchmarks, including the knowledge-based MMLU and the Tool Learning dataset Seal-Tools.
  arXiv  Detail & Related papers  (2025-06-09T08:52:27Z)
• Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers [74.17516978246152]
  Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques.<n>We propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds.<n>Experiments on four knowledge-intensive benchmarks show that EXSEARCH substantially outperforms baselines.
  arXiv  Detail & Related papers  (2025-05-26T15:27:55Z)
• Complex LLM Planning via Automated Heuristics Discovery [48.07520536415374]
  We consider enhancing large language models (LLMs) for complex planning tasks.<n>We propose automated inferences discovery (AutoHD), a novel approach that enables LLMs to explicitly generate functions to guide-time search.<n>Our proposed method requires no additional model training or finetuning--and the explicit definition of functions generated by the LLMs provides interpretability and insights into the reasoning process.
  arXiv  Detail & Related papers  (2025-02-26T16:52:31Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [65.23593936798662]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• ConceptAgent: LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution [33.252158560173655]
  ConceptAgent is a natural language-driven robotic platform designed for task execution in unstructured environments. We present innovations designed to limit shortcomings, including 1) Predicate Grounding to prevent and recover from infeasible actions, and 2) an embodied version of LLM-guided Monte Carlo Tree Search with self reflection.
  arXiv  Detail & Related papers  (2024-10-08T15:05:40Z)
• Spatial Reasoning and Planning for Deep Embodied Agents [2.7195102129095003]
  This thesis explores the development of data-driven techniques for spatial reasoning and planning tasks. It focuses on enhancing learning efficiency, interpretability, and transferability across novel scenarios.
  arXiv  Detail & Related papers  (2024-09-28T23:05:56Z)
• From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems [59.40480894948944]
  Large language model (LLM) empowered agents are able to solve decision-making problems in the physical world. Under this model, the LLM Planner navigates a partially observable Markov decision process (POMDP) by iteratively generating language-based subgoals via prompting. We prove that the pretrained LLM Planner effectively performs Bayesian aggregated imitation learning (BAIL) through in-context learning.
  arXiv  Detail & Related papers  (2024-05-30T09:42:54Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [68.29746557968107]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.<n> Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)

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.