LM4Plan @ AAAI 2025
Accepted Papers
You should be able to view all accepted papers here
Workshop Details
- Venue: AAAI’25 Workshop, Pennsylvania Convention Center, Philadelphia, Pennsylvania, USA
- Date: March 3, 2025, 9am - 6pm.
- Location: Room 117
- Slides upload link (orals): https://aaai-25-slides-upload.paperform.co/
- Posters dimensions: up to 30”x40”, either portrait or landscape.
Preliminary Schedule
List of papers accepted as orals (titles, no author info)
- A Roadmap to Guide the Integration of LLMs in Hierarchical Planning
- ACPBench Hard: Unrestrained Reasoning about Action, Change, and Planning
- ACPBench: Reasoning about Action, Change, and Planning
- Bootstrapping Object-level Planning with Large Language Models
- Conversational Goal-Conflict Explanations in Planning via Multi-Agent LLMs
- Creating PDDL Models from Javascript using LLMs: Preliminary Results
- Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation
- Learning to Reason with Transformers via Search Inductive Biases: A Proposal
- Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts
- Predicate Invention from Pixels via Pretrained Vision-Language Models
- S3E: Semantic Symbolic State Estimation With Vision-Language Foundation Models
- Transition Function Prediction in AI Planning Using LLMs
List of accepted papers as posters (titles, no author info), split into two sessions
Poster session I
- Adaptive Iterative Feedback Prompting for Obstacle-Aware Path Planning via LLMs
- APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents
- Benchmark Real-time Adaptation and Communication Capabilities of Embodied Agent in Collaborative Scenarios
- CAPTAIN: Continuous Automated Planning Through Autonomous Internet Navigation
- DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning
- Factored State Sampling
- Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models
- Leveraging LLMs for Generating Document-Informed Hierarchical Planning Models: A Proposal
- Look Further Ahead: Testing the Limits of GPT-4 in Path Planning
- SFF Rendering-Based Uncertainty Prediction using VisionLLM
Poster session II
- A Critical Assessment of LLMs for Solving Multi-step Problems: Preliminary Results
- CSG-Driver: Common Sense Guided Autonomous Driving under Legal Compliance and Practical Flexibility in Dilemma Situations
- Evaluating the Meta- and Object-Level Reasoning of Large Language Models for Question Answering
- LLMs as Planning Modelers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models
- Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Planning Case Study
- Planning AI Assistant for Emergency Decision-Making (PlanAID): Framing Planning Problems and Assessing Plans with Large Language Models
- Planning with Vision-Language Models and a Use Case in Robot-Assisted Teaching
- Starjob: Dataset for LLM-Driven Job Shop Scheduling
- Towards Siloed LLM-based Systems for Mission-critical Planning
- Towards Zero-Shot, Controllable Dialog Planning with LLMs
Reviewers
| Name | Affilitation |
|---|---|
| Stefan Edelkamp | AIC FEL CTU Prague |
| Vicenç Gomez | Universitat Pompeu Fabra |
| Morgan Fine-Morris | US Naval Research Lab |
| Sarah Keren | Technion |
| Hector Palacios | ServiceNow |
| Shirin Sohrabi | International Business Machines |
| Christian Muise | Queens University |
| Nishanth Kumar | NVIDIA |
| Leslie N. Smith | U. S. Naval Research Laboratory |
| Tom Silver | Princeton University |
| Xiaolin Fang | Massachusetts Institute of Technology |
| Jörg Hoffmann | Saarland University |
| Rebecca Eifler | Saarland University |
| Daniel Fišer | Aalborg University |
| Nir Lipovetzky | The University of Melbourne |
| Jakob Thumm | Technische Universität München |
| Mak Roberts | U. S. Naval Research Laboratory |
| Karthik Valmeekam | Arizona State University |
| Tyler D Comisky | Naval Air Warfare Center Aircraft Division |
| Dillon Ze Chen | LAAS / CNRS |
| Vincent Hsiao | U. S. Naval Research Laboratory |
| Sachin Grover | Arizona State University |
Call for Papers
#### 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.
#### Workshop TopicsWe are welcoming paper submissions on the following topics:
- Planning directly with pre-trained or fine-tuned LLMs.
- LLMs for (partial) model elicitation.
- LLMs for generating structured planning problem descriptions.
- LLMs for search guidance or search pruning.
- Validation/verification of plans, policies, or models.
- Planning for LLMs.
- Using LLMs to develop interfaces for planning-based systems.
- Using LLMs as a proxy for user preferences.
- 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.
Organizing Committee
Sarath Sreedharan, Colorado State University
Jiayuan Mao, MIT
Wenlong Huang, Stanford
Michael Katz, IBM Research
Subbarao Kambhampati, Arizona State University
Please send your inquiries to llmforplanning@gmail.com