SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks

• URL: http://arxiv.org/abs/2605.14051v1
• Date: Wed, 13 May 2026 19:12:24 GMT
• Title: SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks
• Abstract summary: We propose textttSPIN, a planning wrapper that combines validated Directed Acyclic Graph (DAG) planning with prefix based execution control.<n>textttSPIN enforces a strict DAG contract through texttt_validate_plan_text and repair prompting.<n>On AssetOpsBench, across 261 scenarios, textttSPIN reduces tasks executed from 1061 to 623 and improves emphAccomplished from 0.638 to 0.706, while reducing tool calls from 11.81 to
• Score: 1.496156904825668
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Industrial LLM agent systems often separate planning from execution, yet LLM planners frequently produce structurally invalid or unnecessarily long workflows, leading to brittle failures and avoidable tool and API cost. We propose \texttt{SPIN}, a planning wrapper that combines validated Directed Acyclic Graph (DAG) planning with prefix based execution control. \texttt{SPIN} enforces a strict DAG contract through \texttt{\_validate\_plan\_text} and repair prompting, producing executable plans before downstream execution, and then evaluates DAG prefixes incrementally to stop when the current prefix is sufficient to answer the query. On AssetOpsBench, across 261 scenarios, \texttt{SPIN} reduces executed tasks from 1061 to 623 and improves \emph{Accomplished} from 0.638 to 0.706, while reducing tool calls from 11.81 to 6.82 per run. On MCP Bench, the same wrapper improves planning, grounding, and dependency related scores for both GPT OSS1 and Llama 4 Maverick.

Related papers

• When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents [1.7674345486888505]
  We present BRACE, a controller that formulates replanning as a budgeted control loop.<n>We introduce E-RECAP, a cost-aware progressive token pruning method.<n>Across Meta Habitat, RoboFactory, and AirSim, BRACE with E-RECAP reduces replanning-call token counts by 62-92%.
  arXiv  Detail & Related papers  (2026-08-02T18:17:35Z)
• PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems [59.730861364166174]
  PlanBench-XL is an interactive benchmark of 327 retail tasks over 1,665 tools.<n>It tests whether agents can iteratively retrieve usable tools, invoke them to uncover intermediate evidence for subsequent calls toward the final goal.
  arXiv  Detail & Related papers  (2026-06-21T08:29:12Z)
• Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents [40.17728515217378]
  We introduce Agent Planning Benchmark (APB), a planning-specific diagnostic benchmark with 4,209 multimodal cases across 22 domains and five settings.<n>APB reveals systematic weaknesses in long-horizon planning, tool-noise robustness, calibrated refusal, and inference-time refinement.<n>APB serves as an upstream diagnostic complement to execution benchmarks.
  arXiv  Detail & Related papers  (2026-06-03T13:37:47Z)
• PlanCompiler: A Deterministic Compilation Architecture for Structured Multi-Step LLM Pipelines [0.0]
  We present PlanCompiler, a compilation architecture for structured pipelines that separates planning from execution through a typed node registry registry.<n>PlanCompiler produces a typed plan over a fixed registry of primitives, validates that plan against explicit structural and type constraints, and compiles only validated plans into executable Python.
  arXiv  Detail & Related papers  (2026-04-08T00:54:41Z)
• Programming over Thinking: Efficient and Robust Multi-Constraint Planning [54.77940831026738]
  SCOPE is a framework that disentangles query-specific reasoning from generic code execution.<n>SCOPE achieves state-of-the-art performance while lowering cost and latency.
  arXiv  Detail & Related papers  (2026-01-14T02:58:07Z)
• Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents [28.061156787350395]
  Task-Decoupled Planning (TDP) is a training-free framework that replaces entangled reasoning with task decoupling.<n>TDP confines reasoning and replanning to the active sub-task without disrupting the workflow.<n>Results on TravelPlanner, ScienceWorld, and HotpotQA show that TDP outperforms strong baselines while reducing token consumption by up to 82%.
  arXiv  Detail & Related papers  (2026-01-12T14:30:10Z)
• Decompose, Plan in Parallel, and Merge: A Novel Paradigm for Large Language Models based Planning with Multiple Constraints [31.631832677979826]
  We propose a novel parallel planning paradigm, which Decomposes, Plans for subtasks in Parallel, and Merges subplans into a final plan (DPPM)<n>Specifically, DPPM decomposes the complex task based on constraints into subtasks, generates the subplan for each subtask in parallel, and merges them into a global plan.<n> Experimental results demonstrate that DPPM significantly outperforms existing methods in travel planning tasks.
  arXiv  Detail & Related papers  (2025-06-03T09:33:13Z)
• Building a Stable Planner: An Extended Finite State Machine Based Planning Module for Mobile GUI Agent [13.259836345131525]
  We propose SPlanner, a plug-and-play planning module to generate execution plans that guide vision language model(VLMs) in executing tasks.<n>SPlanner achieves a 63.8% task success rate when paired with Qwen2.5-VL-72B as the VLM, yielding a 28.8 percentage point improvement compared to using Qwen2.5-VL-72B without planning assistance.
  arXiv  Detail & Related papers  (2025-05-20T09:45:55Z)
• Plan-over-Graph: Towards Parallelable LLM Agent Schedule [53.834646147919436]
  Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning.<n>This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph.<n>The model then understands this task graph as input and generates a plan for parallel execution.
  arXiv  Detail & Related papers  (2025-02-20T13:47:51Z)
• Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following [62.10809033451526]
  This work focuses on building a task planner for Embodied Instruction Following (EIF) using Large Language Models (LLMs)<n>We frame the task as a Partially Observable Markov Decision Process (POMDP) and aim to develop a robust planner under a few-shot assumption.<n>Our experiments on the ALFRED dataset indicate that our planner achieves competitive performance under a few-shot assumption.
  arXiv  Detail & Related papers  (2024-12-27T10:05:45Z)
• Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
  We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. It achieves a 25.1% relative improvement compared with directly generating responses.
  arXiv  Detail & Related papers  (2024-09-19T04:13:58Z)
• Tree-Planner: Efficient Close-loop Task Planning with Large Language Models [63.06270302774049]
  Tree-Planner reframes task planning with Large Language Models into three distinct phases. Tree-Planner achieves state-of-the-art performance while maintaining high efficiency.
  arXiv  Detail & Related papers  (2023-10-12T17:59:50Z)
• A Feedback Scheme to Reorder a Multi-Agent Execution Schedule by Persistently Optimizing a Switchable Action Dependency Graph [65.70656676650391]
  We consider multiple Automated Guided Vehicles (AGVs) navigating a common workspace to fulfill various intralogistics tasks. One approach is to construct an Action Dependency Graph (ADG) which encodes the ordering of AGVs as they proceed along their routes. If the workspace is shared by dynamic obstacles such as humans or third party robots, AGVs can experience large delays. We present an online method to repeatedly modify acyclic ADG to minimize route completion times of each AGV.
  arXiv  Detail & Related papers  (2020-10-11T14:39:50Z)

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.