mlsanityData to 14 Oct 2026

SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks

arXiv 2605.14051 ↗First posted 13 May 2026cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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 textttSPIN, a planning wrapper that combines validated Directed Acyclic Graph (DAG) planning with prefix based execution control. textttSPIN enforces a strict DAG contract through textttvalidateplantext 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, textttSPIN reduces executed tasks from 1061 to 623 and improves 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 15 of its 18 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

15 of 18 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning15 Mar

Other references · 14

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  4. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 197
  5. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  6. 2024On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Taskscited by 142
  7. 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learningcited by 110
  8. 2025MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Serverscited by 109
  9. 2025JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Modelscited by 71
  10. 2024Thought of Search: Planning with Language Models Through The Lens of Efficiencycited by 32
  11. 2024Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMscited by 29
  12. 2025Learning to Generate Structured Output with Schema Reinforcement Learningcited by 29
2 more
  1. 2025Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instructioncited by 10
  2. 2024Automating Thought of Search: A Journey Towards Soundness and Completenesscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ALAS: Transactional and Dynamic Multi-Agent LLM Planning
  2. 2026Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution
  3. 2026PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
  4. 2026From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution
  5. 2026Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
  6. 2026LeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs
  7. 2024FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
  8. 2024Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs