Paper Feed
================
Must-read papers on LLM-driven automated planning specification.

New Papers!
-------------------------------------------------------
    + **"Make Planning Research Rigorous Again!"** Katz et al. (2025) `[paper] <https://arxiv.org/abs/2505.21674>`__
    + **"Achieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLM"** Attolino et al. (2025) `[paper] <https://arxiv.org/abs/2505.08492>`__ `[code] <https://github.com/NichAttGH/Gideon>`__
    + **"LODGE: Joint Hierarchical Task Planning and Learning of Domain Models with Grounded Execution"** Kienle et al. (2025) `[paper] <https://arxiv.org/abs/2505.13497>`__ `[code] <https://claudius-kienle.github.io/lodge>`__
    + **"Large Language Models for Planning: A Comprehensive and Systematic Survey"** Cao et al. (2025) `[paper] <https://arxiv.org/abs/2505.19683>`__ `[code] <https://github.com/Quester-one/Awesome-LLM-Planning>`__
    + **"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation"** Hu et al. (2025) `[paper] <https://arxiv.org/abs/2502.13092>`__ `[code] <https://github.com/Aaron617/text2world>`__

Paper List
-------------------------------------------------------

This section presents a taxonomy of research within Model Construction, organized into three broad categories: Model Generation, Model Editing, and Model Benchmarks. Within each category, the most recent contributions are listed first (then alphabetically).

**Model Generation**
~~~~~~~~~~~~~~~~~~~~

**Task Modeling**

.. raw:: html

    <div style="max-height: 300px; overflow-y: auto; border: 1px solid #ccc; padding: 10px; margin-bottom: 1em;">

.. list-table::

    * - **"Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation"** Wang et al. (2025)
      - `[paper] <https://arxiv.org/abs/2503.08084>`__ `[code] <https://nicehiro.github.io/IALP/#>`__
    * - **"TIC: Translate-Infer-Compile for accurate 'text to plan' using LLMs and logical intermediate representations"** Agarwal and Sreepathy (2024)
      - `[paper] <https://arxiv.org/abs/2402.06608>`__
    * - **"AutoGPT+P: Affordance-based Task Planning with Large Language Models"** Birr et al. (2024)
      - `[paper] <https://arxiv.org/abs/2402.10778>`__ `[code] <https://git.h2t.iar.kit.edu/sw/autogpt-p>`__
    * - **"Leveraging LLMs for Generating Document-Informed Hierarchical Planning Models: A Proposal"** Fine-Morris et al. (2024)
      - `[paper] <https://openreview.net/forum?id=QQltS3Nxj9&referrer=%5Bthe%20profile%20of%20Laura%20M.%20Hiatt%5D(%2Fprofile%3Fid%3D~Laura_M._Hiatt1)>`__
    * - **"A Demonstration of Natural Language Understanding in Embodied Planning Agents"** Grover and Mohan (2024)
      - `[paper] <https://openreview.net/forum?id=62frmxeAPp>`__
    * - **"CaStL: Constraints as Specifications through LLM Translation for Long-Horizon Task and Motion Planning"** Guo et al. (2024)
      - `[paper] <https://arxiv.org/abs/2410.22225>`__
    * - **"PlanCollabNL: Leveraging Large Language Models for Adaptive Plan Generation in Human-Robot Collaboration"** Izquierdo-Badiola et al. (2024)
      - `[paper] <https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10610055>`__
    * - **"Enabling Semantic Reasoning in Robots through Natural Language Processing"** Kalland (2024)
      - `[paper] <https://ntnuopen.ntnu.no/ntnu-xmlui/handle/11250/3157083>`__
    * - **"Thought of Search: Planning with Language Models Through The Lens of Efficiency"** Katz et al. (2024)
      - `[paper] <https://arxiv.org/abs/2404.11833>`__
    * - **"Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decomposition"** Kwon et al. (2024)
      - `[paper] <https://arxiv.org/abs/2409.19250>`__ `[code] <http://graphics.ewha.ac.kr/LLMTAMP/>`__
    * - **"Planning AI Assistant for Emergency Decision-Making (PlanAID): Framing Planning Problems and Assessing Plans with Large Language Models"** Lee et al. (2024)
      - `[paper] <https://openreview.net/forum?id=LebubIfqae>`__
    * - **"Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning"** Li et al. (2024)
      - `[paper] <https://arxiv.org/abs/2411.06920>`__
    * - **"Towards Human Awareness in Robot Task Planning with Large Language Models"** Liu et al. (2024)
      - `[paper] <https://arxiv.org/abs/2404.11267>`__
    * - **"LLM Reasoner and Automated Planner: A New NPC Approach"** Merino and Sabater-Mir (2024)
      - `[paper] <https://arxiv.org/abs/2501.10106>`__
    * - **"Bootstrapping Object-level Planning with Large Language Models"** Paulius et al. (2024)
      - `[paper] <https://arxiv.org/abs/2409.12262>`__
    * - **"TRIP-PAL: Travel Planning with Guarantees by Combining Large Language Models and Automated Planners"** Rosa et al. (2024)
      - `[paper] <https://arxiv.org/abs/2406.10196>`__
    * - **"TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models"** Singh et al. (2024)
      - `[paper] <https://arxiv.org/abs/2403.17246>`__ `[code] <https://glamor-usc.github.io/twostep/>`__
    * - **"Anticipate & Collab: Data-driven Task Anticipation and Knowledge-driven Planning for Human-robot Collaboration"** Singh et al. (2024)
      - `[paper] <https://arxiv.org/abs/2404.03587>`__ `[code] <https://github.com/dataplan-hrc/DaTAPlan>`__
    * - **"PDDLEGO: Iterative Planning in Textual Environments"** Zhang et al. (2024)
      - `[paper] <https://arxiv.org/abs/2405.19793>`__ `[code] <https://github.com/zharry29/nl-to-pddl>`__
    * - **"LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner"** Zhang et al. (2024)
      - `[paper] <https://arxiv.org/abs/2409.20560>`__ `[code] <https://drive.google.com/drive/folders/1dFfwJve4isw8E92bEQCSxIcQLmax-mqM>`__
    * - **"LGMCTS: Language-Guided Monte-Carlo Tree Search for Executable Semantic Object Rearrangement"** Chang et al. (2023)
      - `[paper] <https://arxiv.org/abs/2309.15821>`__ `[code] <https://github.com/changhaonan/LGMCTS-D>`__
    * - **"AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers"** Chen et al. (2023)
      - `[paper] <https://arxiv.org/abs/2306.06531>`__ `[code] <https://github.com/yongchao98/AutoTAMP>`__
    * - **"Dynamic Planning with a LLM"** Dagan et al. (2023)
      - `[paper] <https://arxiv.org/abs/2308.06391>`__ `[code] <https://github.com/itl-ed/llm-dp>`__
    * - **"Task and Motion Planning with Large Language Models for Object Rearrangement"** Ding et al. (2023)
      - `[paper] <https://arxiv.org/abs/2303.06247>`__ `[code] <https://sites.google.com/view/llm-grop>`__
    * - **"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency"** Liu et al. (2023)
      - `[paper] <https://arxiv.org/abs/2304.11477>`__ `[code] <https://github.com/Cranial-XIX/llm-pddl>`__
    * - **"Faithful Chain-of-Thought Reasoning"** Lyu et al. (2023)
      - `[paper] <https://arxiv.org/abs/2301.13379>`__ `[code] <https://github.com/veronica320/faithful-cot>`__
    * - **"Vision-Language Interpreter for Robot Task Planning"** Shirai et al. (2023)
      - `[paper] <https://arxiv.org/abs/2311.00967>`__ `[code] <https://github.com/omron-sinicx/ViLaIn>`__
    * - **"Translating natural language to planning goals with large-language models"** Xie et al. (2023)
      - `[paper] <https://arxiv.org/abs/2302.05128>`__ `[code] <https://github.com/clear-nus/gpt-pddl>`__
    * - **"Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behaviour in out-of-distribution reasoning tasks"** Collins et al. (2022)
      - `[paper] <https://arxiv.org/abs/2205.05718>`__ `[code] <https://github.com/collinskatie/structured_flexible_and_robust>`__

.. raw:: html

    </div>

**Domain Modeling**

.. raw:: html

    <div style="max-height: 300px; overflow-y: auto; border: 1px solid #ccc; padding: 10px; margin-bottom: 1em;">

.. list-table::

    * - **"Predicate Invention from Pixels via Pretrained Vision-Language Models"** Athalye et al. (2024)
      - `[paper] <https://arxiv.org/abs/2501.00296v1>`__
    * - **"Language-Augmented Symbolic Planner for Open-World Task Planning"** Chen at al. (2024)
      - `[paper] <https://arxiv.org/abs/2407.09792>`__
    * - **"Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts"** Huang et al. (2024)
      - `[paper] <https://arxiv.org/abs/2409.15915>`__ `[code] <https://github.com/Sino-Huang/Official-LLM-Symbolic-Planning-without-Experts>`__
    * - **"Learning Compositional Behaviors from Demonstration and Language"** Liu et al. (2024)
      - `[paper] <https://blade-bot.github.io>`__
    * - **"Using Large Language Models to Extract Planning Knowledge from Common Vulnerabilities and Exposures"** Oates et al. (2024)
      - `[paper] <https://icaps24.icaps-conference.org/program/workshops/keps-papers/KEPS-24_paper_12.pdf>`__ `[code] <https://github.com/ronwalf/CLLaMP>`__
    * - **"Large Language Models as Planning Domain Generators"** Oswald et al. (2024)
      - `[paper] <https://arxiv.org/abs/2405.06650>`__ `[code] <https://github.com/IBM/NL2PDDL>`__
    * - **"Autonomously Learning World-Model Representations For Efficient Robot Planning"** Shah (2024)
      - `[paper] <https://keep.lib.asu.edu/items/193613>`__
    * - **"Creating PDDL Models from Javascript using LLMs: Preliminary Results"** Sikes et al. (2024)
      - `[paper] <https://openreview.net/forum?id=VyTxXSPmbE&referrer=%5Bthe%20profile%20of%20Kelsey%20Sikes%5D(%2Fprofile%3Fid%3D~Kelsey_Sikes1)>`__
    * - **"Leveraging LLMs for HTN domain model generation via prompt engineering"** Sinha (2024)
      - `[paper] <https://elib.uni-stuttgart.de/items/b1534c2c-9310-4348-8202-5db21d219a49>`__
    * - **"Making Large Language Models into World Models with Precondition and Effect Knowledge"** Xie at al. (2024)
      - `[paper] <https://arxiv.org/abs/2409.12278>`__
    * - **"PROC2PDDL: Open-Domain Planning Representations from Texts"** Zhang et al. (2024)
      - `[paper] <https://arxiv.org/abs/2403.00092>`__ `[code] <https://github.com/zharry29/proc2pddl>`__
    * - **"Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds"** Ding et al. (2023)
      - `[paper] <https://arxiv.org/abs/2305.17590>`__ `[code] <https://github.com/yding25/GPT-Planner>`__
    * - **"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning"** Guan et al. (2023)
      - `[paper] <https://arxiv.org/abs/2305.14909>`__ `[code] <https://github.com/GuanSuns/LLMs-World-Models-for-Planning>`__
    * - **"Learning adaptive planning representations with natural language guidance"** Wong et al. (2023)
      - `[paper] <https://arxiv.org/abs/2312.08566>`__

.. raw:: html

    </div>

**Hybrid Modeling**

.. raw:: html

    <div style="max-height: 300px; overflow-y: auto; border: 1px solid #ccc; padding: 10px; margin-bottom: 1em;">

.. list-table::

    * - **"NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions"** Gestrin et al. (2024)
      - `[paper] <https://arxiv.org/abs/2405.04215>`__ `[code] <https://github.com/mrlab-ai/NL2Plan>`__
    * - **"InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning"** Han et al. (2024)
      - `[paper] <https://interpret-robot.github.io>`__ `[code] <https://github.com/hmz-15/interactive-predicate-learning>`__
    * - **"Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming"** Hao et al. (2024)
      - `[paper] <https://arxiv.org/abs/2410.12112>`__ `[code] <https://github.com/yih301/LLMFP>`__
    * - **"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation"** Hu et al. (2024)
      - `[paper] <https://arxiv.org/abs/2408.00764>`__ `[code] <https://github.com/Aaron617/AgentGen>`__
    * - **"DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models"** Liu et al. (2024)
      - `[paper] <https://arxiv.org/abs/2404.03275>`__
    * - **"Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models"** Mahdavi et al. (2024)
      - `[paper] <https://arxiv.org/abs/2407.12979>`__
    * - **"Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability"** Sakib and Sun (2024)
      - `[paper] <https://arxiv.org/abs/2401.07868>`__
    * - **"Toward a Method to Generate Capability Ontologies from Natural Language Descriptions"** Silva et al. (2024)
      - `[paper] <https://arxiv.org/abs/2406.07962>`__
    * - **"Generating consistent PDDL domains with Large Language Models"** Smirnov et al. (2024)
      - `[paper] <https://arxiv.org/abs/2404.07751>`__
    * - **"MORPHeus: a Multimodal One-armed Robot-assisted Peeling System with Human Users In-the-loop"** Ye et al. (2024)
      - `[paper] <https://emprise.cs.cornell.edu/morpheus/>`__ `[code] <https://emprise.cs.cornell.edu/morpheus/>`__
    * - **"There and Back Again: Extracting Formal Domains for Controllable Neurosymbolic Story Authoring"** Kelly et al. (2023)
      - `[paper] <https://ojs.aaai.org/index.php/AIIDE/article/view/27502/27275>`__ `[code] <https://github.com/alex-calderwood/there-and-back>`__
    * - **"The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs"** Ying et al. (2023)
      - `[paper] <https://arxiv.org/abs/2306.14325>`__
    * - **"ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning"** Zhou et al. (2023)
      - `[paper] <https://arxiv.org/abs/2308.13724>`__ `[code] <https://github.com/ma-labo/ISR-LLM>`__

.. raw:: html

    </div>

----

**Model Editing**
~~~~~~~~~~~~~~~~~

.. raw:: html

    <div style="max-height: 300px; overflow-y: auto; border: 1px solid #ccc; padding: 10px; margin-bottom: 1em;">

.. list-table::

    * - **"Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning"** Caglar et al. (2024)
      - `[paper] <https://arxiv.org/abs/2311.13720>`__
    * - **"LLMs for AI Planning: A Study on Error Detection and Correction in PDDL Domain Models"** Patil (2024)
      - `[paper] <https://elib.uni-stuttgart.de/server/api/core/bitstreams/efc35e23-7aec-4056-8de6-a56ba5b53249/content>`__
    * - **"Traversing the Linguistic Divide: Aligning Semantically Equivalent Fluents Through Model Refinement"** Sikes et al. (2024)
      - `[paper] <https://drive.google.com/file/d/1gd7DOHY6ztiTO1jllDOmP-V8V-q1N0uG/view>`__
    * - **"Exploring the limitations of using large language models to fix planning tasks"** Gragera and Pozanco (2023)
      - `[paper] <https://icaps23.icaps-conference.org/program/workshops/keps/KEPS-23_paper_3645.pdf>`__

.. raw:: html

    </div>

----

**Model Benchmarks**
~~~~~~~~~~~~~~~~~~~~

**LLMs-as-Planners**

.. raw:: html

    <div style="max-height: 300px; overflow-y: auto; border: 1px solid #ccc; padding: 10px; margin-bottom: 1em;">

.. list-table::

    * - **"A Roadmap to Guide the Integration of LLMs in Hierarchical Planning"** Puerta-Merino et al. (2025)
      - `[paper] <https://arxiv.org/abs/2501.08068>`__ `[code] <https://github.com/Corkiray/HTN-LLM>`__
    * - **"Exploring and Benchmarking the Planning Capabilities of Large Language Models"** Bohnet et al. (2024)
      - `[paper] <https://arxiv.org/abs/2406.13094>`__
    * - **"ACPBench: Reasoning about Action, Change, and Planning"** Kokel et al. (2024)
      - `[paper] <https://arxiv.org/abs/2410.05669>`__ `[code] <https://github.com/IBM/ACPBench>`__
    * - **"TravelPlanner: A Benchmark for Real-World Planning with Language Agents"** Xie et al. (2024)
      - `[paper] <https://openreview.net/forum?id=l5XQzNkAOe>`__ `[code] <https://github.com/OSU-NLP-Group/TravelPlanner>`__
    * - **"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning"** Zheng et al. (2024)
      - `[paper] <https://arxiv.org/abs/2406.04520>`__ `[code] <https://github.com/google-deepmind/natural-plan>`__
    * - **"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning"** (Household) Guan et al. (2023)
      - `[paper] <https://arxiv.org/abs/2305.14909>`__ `[code] <https://github.com/GuanSuns/LLMs-World-Models-for-Planning>`__
    * - **"Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planning"** Stein et al. (2023)
      - `[paper] <https://arxiv.org/abs/2311.09830>`__ `[code] <https://github.com/minecraft-saar/autoplanbench>`__
    * - **"ON THE PLANNING ABILITIES OF LARGE LANGUAGE MODELS (A CRITICAL INVESTIGATION WITH A PROPOSED BENCHMARK)"** Valmeekam et al. (2023)
      - `[paper] <https://arxiv.org/pdf/2302.06706>`__ `[code] <https://github.com/karthikv792/LLMs-Planning>`__
    * - **"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change"** Valmeekam et al. (2023)
      - `[paper] <https://papers.nips.cc/paper_files/paper/2023/hash/7a92bcdede88c7afd108072faf5485c8-Abstract-Datasets_and_Benchmarks.html>`__ `[code] <https://github.com/karthikv792/LLMs-Planning>`__
    * - **"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning"** Shridhar et al. (2021)
      - `[paper] <https://arxiv.org/abs/2010.03768>`__ `[code] <https://github.com/alfworld/alfworld>`__

.. raw:: html

    </div>

**LLMs-as-Formalizers PDDL Benchmarks**

.. raw:: html

    <div style="max-height: 300px; overflow-y: auto; border: 1px solid #ccc; padding: 10px; margin-bottom: 1em;">

.. list-table::

    * - **"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation"** Hu et al. (2025)
      - `[paper] <https://arxiv.org/abs/2502.13092>`__ `[code] <https://github.com/Aaron617/text2world>`__
    * - **"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages"** Zuo et al. (2024)
      - `[paper] <https://arxiv.org/abs/2407.03321>`__ `[code] <https://github.com/batsresearch/planetarium>`__

.. raw:: html

    </div>

The following is the core summary of model generation frameworks in `"LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models" <https://arxiv.org/abs/2503.18971v1>`_:

.. image:: _static/survey_table.png
   :alt: no image available