mlsanityData to 14 Oct 2026

ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning

arXiv 2308.13724 ↗First posted 26 Aug 2023cs.RO cs.AIcited by 77

Not on the map. Why?

Abstract (arXiv)

Motivated by the substantial achievements observed in Large Language Models (LLMs) in the field of natural language processing, recent research has commenced investigations into the application of LLMs for complex, long-horizon sequential task planning challenges in robotics. LLMs are advantageous in offering the potential to enhance the generalizability as task-agnostic planners and facilitate flexible interaction between human instructors and planning systems. However, task plans generated by LLMs often lack feasibility and correctness. To address this challenge, we introduce ISR-LLM, a novel framework that improves LLM-based planning through an iterative self-refinement process. The framework operates through three sequential steps: preprocessing, planning, and iterative self-refinement. During preprocessing, an LLM translator is employed to convert natural language input into a Planning Domain Definition Language (PDDL) formulation. In the planning phase, an LLM planner formulates an initial plan, which is then assessed and refined in the iterative self-refinement step by using a validator. We examine the performance of ISR-LLM across three distinct planning domains. The results show that ISR-LLM is able to achieve markedly higher success rates in task accomplishments compared to state-of-the-art LLM-based planners. Moreover, it also preserves the broad applicability and generalizability of working with natural language instructions.

Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). Builds on 29 of its 55 references that are in the map. First posted on arXiv 26 Aug 2023.

Builds on

29 of 55 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  8. 2019Language Models as Knowledge Bases?cited by 1,936
  9. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  10. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  11. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  12. 2022Large Language Models Can Self-Improvecited by 664
17 more
  1. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
  2. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  3. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 501
  4. 2020Integrated Task and Motion Planningcited by 290
  5. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 242
  6. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 224
  7. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 221
  8. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
  9. 2018PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planningcited by 150
  10. 2023Task and Motion Planning with Large Language Models for Object Rearrangementcited by 141
  11. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  12. 2021Skill Induction and Planning with Latent Languagecited by 99
  13. 2018Task Planning in Robotics: an Empirical Comparison of PDDL-based and ASP-based Systemscited by 40
  14. 2021Long-Horizon Multi-Robot Rearrangement Planning for Construction Assemblycited by 24
  15. 2021Generalized Planning as Heuristic Searchcited by 18
  16. 2020Task-Motion Planning for Safe and Efficient Urban Drivingcited by 7
  17. 2023Symbolic State Space Optimization for Long Horizon Mobile Manipulation Planningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 25; 2025: 27; 2026: 23.

77 papers.

Sort:

By area:

  1. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  2. 2024A Survey on Self-Evolution of Large Language Modelscited by 91
  3. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 83
  4. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 57
  5. 2024A Survey on Robotics with Foundation Models: toward Embodied AIcited by 56
  6. 2024Towards Efficient LLM Grounding for Embodied Multi-Agent Collaborationcited by 45
  7. 2024VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulationcited by 45
  8. 2024On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)cited by 40
  9. 2025LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Modelscited by 38
  10. 2024Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programmingcited by 35
  11. 2024LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Plannercited by 32
  12. 2025LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Taskscited by 26
38 more
  1. 2023Mathematical Language Models: A Surveycited by 24
  2. 2024Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMscited by 22
  3. 2024NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptionscited by 22
  4. 2025Virtual Agent Economiescited by 21
  5. 2024AutoGPT+P: Affordance-based Task Planning with Large Language Modelscited by 19
  6. 2026AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robotscited by 16
  7. 2025Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planningcited by 15
  8. 2025A Survey on Mathematical Reasoning and Optimization with Large Language Modelscited by 12
  9. 2025Feedback Friction: LLMs Struggle to Fully Incorporate External Feedbackcited by 11
  10. 2025AIR: Complex Instruction Generation via Automatic Iterative Refinementcited by 10
  11. 2024LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planningcited by 9
  12. 2024LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic Manipulationcited by 9
  13. 2025Multi-Agent Systems for Robotic Autonomy with LLMscited by 9
  14. 2024Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMscited by 8
  15. 2024Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hackcited by 8
  16. 2025REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulationcited by 8
  17. 2025LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systemscited by 8
  18. 2024Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Librariescited by 7
  19. 2025Procedural Knowledge Improves Agentic LLM Workflowscited by 7
  20. 2024Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forwardcited by 6
  21. 2025CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environmentscited by 6
  22. 2025Toward Super Agent System with Hybrid AI Routerscited by 6
  23. 2025LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planningcited by 6
  24. 2024Dual-AEB: Synergizing Rule-Based and Multimodal Large Language Models for Effective Emergency Brakingcited by 5
  25. 2024Visual Prompting with Iterative Refinement for Design Critique Generationcited by 5
  26. 2025Cost-Awareness in Tree-Search LLM Planning: A Systematic Studycited by 5
  27. 2025Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaborationcited by 5
  28. 2024A Study on Training and Developing Large Language Models for Behavior Tree Generationcited by 4
  29. 2025LLMPC: Large Language Model Predictive Controlcited by 4
  30. 2025Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPscited by 4
  31. 2024Can LLMs plan paths with extra hints from solvers?cited by 3
  32. 2025Performant LLM Agentic Framework for Conversational AIcited by 3
  33. 2024TIC: Translate-Infer-Compile for accurate "text to plan" using LLMs and Logical Representationscited by 2
  34. 2025Self-Corrective Task Planning by Inverse Prompting with Large Language Modelscited by 2
  35. 2025EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environmentscited by 2
  36. 2025Can AI expose tax loopholes? Towards a new generation of legal policy assistantscited by 2
  37. 2025DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulationcited by 2
  38. 2026SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systemscited by 2

50 most cited of 77 All 77 (JSON)