Image de couverture de livre

Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Göbel, Kai, Lorang, Pierrick, Zips, Patrik, Glück, Tobias
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulation
par: Lorang, Pierrick, et autres
Publié: (2026)

Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
par: Goebel, Kai, et autres
Publié: (2025)

Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Robotics
par: Lorang, Pierrick
Publié: (2026)

Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation
par: Lorang, Pierrick, et autres
Publié: (2025)

Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Acting
par: Lorang, Pierrick, et autres
Publié: (2025)

Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning
par: Lu, Hong, et autres
Publié: (2026)

The Universal PDDL Domain
par: Haslum, Patrik, et autres
Publié: (2024)

Toward PDDL Planning Copilot
par: Benyamin, Yarin, et autres
Publié: (2025)

Learning Interpretable Classifiers for PDDL Planning
par: Lequen, Arnaud
Publié: (2024)

Real-World Planning with PDDL+ and Beyond
par: Piotrowski, Wiktor, et autres
Publié: (2024)

Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planning
par: Stein, Katharina, et autres
Publié: (2023)

Compiling Temporal Numeric Planning into Discrete PDDL+: Extended Version
par: Micheli, Andrea, et autres
Publié: (2026)

End-to-end PDDL Planning with Hardcoded and Dynamic Agents
par: La Malfa, Emanuele, et autres
Publié: (2025)

GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models
par: Murray, Andrew, et autres
Publié: (2026)

Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
par: Chen, Dillon Z., et autres
Publié: (2025)

Aligning LLM+PDDL Symbolic Plans with Human Objective Specifications through Evolutionary Algorithm Guidance
par: Burns, Owen, et autres
Publié: (2024)

From An LLM Swarm To A PDDL-Empowered HIVE: Planning Self-Executed Instructions In A Multi-Modal Jungle
par: Vyas, Kaustubh, et autres
Publié: (2024)

Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving
par: Zhou, Kuo, et autres
Publié: (2025)

From Capability Models to Automated Planning: An AAS-Native Approach for Automatic PDDL Generation
par: Nabizada, Hamied, et autres
Publié: (2026)

BPMN to PDDL: Translating Business Workflows for AI Planning
par: Nie, Jasper, et autres
Publié: (2025)

Integrating AI Planning Semantics into SysML System Models for Automated PDDL File Generation
par: Nabizada, Hamied, et autres
Publié: (2025)

Preference Elicitation for Step-Wise Explanations in Logic Puzzles
par: Foschini, Marco, et autres
Publié: (2025)

Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization
par: Wang, Yibo, et autres
Publié: (2026)

DUPLEX: Agentic Dual-System Planning via LLM-Driven Information Extraction
par: Hua, Keru, et autres
Publié: (2026)

Playing Angry Birds with a Domain-Independent PDDL+ Planner
par: Piotrowski, Wiktor, et autres
Publié: (2021)

Safe Learning of PDDL Domains with Conditional Effects -- Extended Version
par: Mordoch, Argaman, et autres
Publié: (2024)

Generating consistent PDDL domains with Large Language Models
par: Smirnov, Pavel, et autres
Publié: (2024)

TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision
par: Zhou, Ruiwen, et autres
Publié: (2024)

SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs
par: Czakó, Patrik, et autres
Publié: (2025)

PDDL Axioms Are Equivalent to Least Fixed Point Logic (Extended Version)
par: Grundke, Claudia, et autres
Publié: (2025)

An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs
par: Vyas, Kaustubh, et autres
Publié: (2025)

Model-based Workflow for the Automated Generation of PDDL Descriptions
par: Nabizada, Hamied, et autres
Publié: (2024)

PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language
par: Shi, Guangyao, et autres
Publié: (2025)

StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization
par: Wang, Ziliang, et autres
Publié: (2025)

StepMathAgent: A Step-Wise Agent for Evaluating Mathematical Processes through Tree-of-Error
par: Yang, Shu-Xun, et autres
Publié: (2025)

Agentic Frameworks for Reasoning Tasks: An Empirical Study
par: Rasheed, Zeeshan, et autres
Publié: (2026)

Characterising LLM-Generated Competency Questions: a Cross-Domain Empirical Study using Open and Closed Models
par: Alharbi, Reham, et autres
Publié: (2026)

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
par: Rahimi, Eliron, et autres
Publié: (2026)

Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment
par: Feng, Zhanbo, et autres
Publié: (2023)

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty
par: Wu, Peilin, et autres
Publié: (2025)