Workshop on Planning in the Era of LLMs (LM4Plan @ ICAPS 2025)

ICAPS 2025 Workshop, Melbourne, Australia, Date: 10-11 November, 2025

Visit https://llmforplanning.github.io/ for up-to-date information.

Overview

Large Language Models (LLMs) are a disruptive force, changing how research was done in many sub-areas of AI. Planning is one of the last bastions that remain standing. The focus of this workshop is on the questions in the intersection of these areas. Some of the specific areas we would like to gain a better understanding in include: what LLMs can contribute to planning, how LLMs can/should be used, what are the pitfalls of using LLMs, what are the guarantees that can be obtained.

Topics of Interest

We invite paper submissions on the following (not exhaustive) list of topics:

• Algorithms and theories of planning with pre-trained or fine-tuned LLMs.
• LLMs for (partial) model elicitation.
• LLMs for search guidance or search pruning.
• LLMs for planning modulo theories.
• LLMs as proxies for user preferences.
• Validation/verification of plans, policies, or models.
• Generalization in planning and generalized planning with LLMs.
• Using LLMs to develop interfaces for planning-related problems.
• Other applications of LLMs in planning.
• Other applications of large vision-language models (VLMs) in planning.
• Planning for LLMs and VLMs.

Important Dates

• Paper submission deadline: August 5th, 2025, AoE (extended)
• Paper acceptance notification: September 8th, 2025, AoE

ICAPS will be in-person this year. Authors of accepted workshop papers are expected to register for the workshop, physically attend the conference and present in person.

Submission Details

We solicit workshop paper submissions relevant to the above call of the following types:

• Long papers – up to 8 pages + unlimited references / appendices
• Short papers – up to 4 pages + unlimited references / appendices

Please format submissions in AAAI style (see instructions in the Author Kit of the ICAPS 2025 Call for Papers). Authors submitting papers rejected from other conferences, please ensure you do your utmost to address the comments given by the reviewers. Please do not submit papers that are already accepted for the main ICAPS conference to the workshop.

Paper submissions should be made through OpenReview.

Accepted Papers

• PDDL-Instruct: Enhancing Symbolic Planning Capabilities in LLMs through Logical Chain-of-Thought Instruction Tuning
  Pulkit Verma, Ngoc La, Anthony Favier, Swaroop Mishra, Julie Shah
• Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
  Dillon Ze Chen, Johannes Zenn, Tristan Cinquin, Sheila A. McIlraith
• Planner-Independent Extraction of Goals and Constraints from Natural Language for Open-World Mobile Robot Missions
  Björn Döschl, Jane Jean Kiam
• Game of Thought: Robust Information Seeking with Large Language Models Using Game Theory
  Langyuan Cui, Hwee Tou Ng, Chun Kai Ling
• Automated Repair of Totally-Ordered Hierarchical Task Network Domains via Context-Free Grammars with Large Language Model Support
  Daniel Lutalo, Pascal Bercher
• Which LLM is Best for Translating Natural Language Goals to PDDL
  Tomas Balyo, Lukas Chrpa, G Michael Youngblood
• Improved Generalized Planning with LLMs through Strategy Refinement and Reflection
  Katharina Stein, Nils Hodel, Daniel Fišer, Jörg Hoffmann, Michael Katz, Alexander Koller
• From Next Token Prediction to (STRIPS) World Models – Preliminary Results
  Carlos Núñez-Molina, Vicenç Gomez, Hector Geffner
• A Collaborative Numeric Task Planning Framework based on Constraint Translations using LLMs
  Anthony Favier, Ngoc La, Pulkit Verma, Julie Shah
• Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game
  Michael Katz, Harsha Kokel, Sarath Sreedharan
• Guiding Exploration in Reinforcement Learning Through LLM-Augmented Observations
  Vaibhav Jain, Gerrit Großmann
• Towards a General Framework for HTN Modeling with LLMs
  Israel Puerta-Merino, Carlos Núñez-Molina, Pablo Mesejo, Juan Fernandez-Olivares
• A Requirements Engineering-Driven Methodology for Planning Domain Generation via LLMs with Invariant-Based Refinement
  Angelo Casciani, Giuseppe De Giacomo, Andrea Marrella, Christoph Weinhuber
• Enhancing GPT-based Planning Policies by Model-based Plan Validation
  Nicholas Rossetti, Massimiliano Tummolo, Alfonso Gerevini, Matteo Olivato, Luca Putelli, Ivan Serina

The papers will be available only after the workshop.

Invited Talk

Towards Model-Based Reasoning in Large Language Models: A Planning Perspective, by Nir Lipovetzky

Abstract: Large Language Models (LLMs) are powerful at generating text, code, and explanations, yet when it comes to structured reasoning, they often provide incorrect responses. In this talk, we explore how ideas from automated planning can help LLMs find structure in queries. We begin with Planning in the Dark, where LLMs infer planning models from natural language, and their non-determinism becomes a feature rather than a flaw with the restraints of conformal prediction and symbolic planners. Next, through Planning-Driven Programming, we show how planning-inspired techniques can guide LLMs to iteratively refine code through reasoning and verification steps. Finally, we turn to the Abstraction and Reasoning Corpus (ARC), demonstrating how planning and knowledge augmentation can enhance compositional reasoning and generalisation beyond training data. Research in AI planning outlines a path toward LLMs that don’t just generate the next token, but also plan, reason, and generalise with the assistance of model based planning solvers.

Bio: Nir Lipovetzky is an Associate Professor in the School of Computing and Information Systems at the University of Melbourne. His research spans artificial intelligence (AI) planning, heuristic search, learning, verification, and intention recognition, with a particular focus on developing novel approaches to inference in sequential decision-making problems. He contributes to several AI planning initiatives, including the Lightweight Automated Planning ToolKiT (LAPKT), designed to simplify the creation and extension of automated planners; Planimation, a platform for visualising plans using declarative programming; and planning.domains, a widely used suite of tools for teaching AI planning. He is passionate about building bridges between AI planning and other research areas.

Schedule

Presentation instructions

All authors must present their papers. The oral presentations are 20 minutes + 5 minutes for questions. The poster presentations get a 2-minute spotlight presentation and must present a poster at the poster session.

The conference organizers will provide us with panels of size 1.8m (H) x 1.2m (W) (from the floor) to put the posters on. There are no size limitations beyond being able to fit on the panel.

Organizing Committee

• Pascal Bercher, Australian National Univeristy
• Augusto B. Corrêa, University of Oxford
• Morgan Fine-Morris, Naval Research Laboratory
• Michael Katz, IBM Research
• Sarath Sreedharan, Colorado State University