LM4Plan @ ICML 2026 (Proposal)

Overview

Language Models (LMs) are a disruptive force, changing how research was done in many subareas 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 LMs can contribute to planning, how LMs can/should be used, what are the pitfalls of using LMs, what are the guarantees that can be obtained.

Tentative Schedule

Time Session
08:00–08:10 Opening Remarks
08:10–09:00 Oral Presentations from selected submissions
09:00–09:30 Keynote Talk: Subbarao Kambhampati, Arizona State University
09:30–10:00 Keynote Talk: Samy Bengio, Apple
10:00–10:30 Keynote Talk: Noam Brown, OpenAI
10:30–11:00 Keynote Talk: Yoav Shoham, Stanford University and AI21 Labs
11:00–12:00 Oral Presentations from selected submissions
12:00–13:00 Lunch
13:00–13:30 Keynote Talk: Peter Stone, University of Texas at Austin
13:30–14:00 Lightning Talks from selected short submissions
14:00–15:00 Panel Discussion: including all invited speakers and panelists
15:00–15:30 Coffee Break + Posters
15:30–16:30 Poster Session including all accepted works
16:30–17:00 Round Table + Closing Remarks

Invited Speakers

Samy Bengio

  • Affiliation: Apple
  • Bio: Samy Bengio is a senior director of ML research at Apple since 2021, and Adjunct Professor at EPFL, Switzerland, since 2024. Previously, he was a distinguished scientist at Google Research since 2007 where he was heading part of the Google Brain team. Before that, he was at IDIAP, where he co-created the famous open-source Torch library. He is interested in many areas of machine learning research, such as deep architectures, representation learning, vision and language processing, and reasoning.

Noam Brown

  • Affiliation: OpenAI
  • Bio: Noam Brown is a Research Scientist at OpenAI working on multi-step reasoning, self-play, and multi-agent AI. He previously worked at FAIR (Meta), where he helped developing CICERO, the first AI to achieve human-level performance in the strategy game Diplomacy. He was also part of the project that created the first AI to defeat top humans in no-limit poker.

Yoav Shoham

  • Affiliation: Stanford University and AI21 Labs
  • Bio: Yoav Shoham is professor emeritus of computer science at Stanford University. Prof. Shoham is Fellow of AAAI, ACM and the Game Theory Society. He has received several prestigious awards during his career, including: the IJCAI Research Excellence Award, the AAAI/ACM Allen Newell Award, and the ACM/SIGAI Autonomous Agents Research Award. Prof. Shoham has founded several AI companies. He also chairs the AI Index initiative, which tracks global AI progress, and WeCode, a nonprofit initiative to train high-quality programmers from disadvantaged populations.

Peter Stone

  • Affiliation: University of Texas at Austin
  • Bio: Peter Stone is the founder and director of the Learning Agents Research Group (LARG) within the Artificial Intelligence Laboratory in the Department of Computer Science at The University of Texas at Austin, as well as Department Chair and Founding Director of Texas Robotics. He was also a co-founder of Cogitai, Inc. and is now Chief Scientist of Sony AI. His research focuses mainly on machine learning, multiagent systems, and robotics.

Subbarao Kambhampati

  • Affiliation: Arizona State University
  • Bio: Subbarao Kambhampati is a professor of computer science at Arizona State University. Kambhampati studies fundamental problems in planning and decision making, motivated in particular by the challenges of human-aware AI systems. He is a fellow of AAAI, AAAS, and ACM, and was an NSF Young Investigator. He was the president of the Association for the Advancement of Artificial Intelligence (AAAI), trustee of International Joint Conference on Artificial Intelligence, and a founding board member of Partnership on AI. Kambhampati’s research as well as his views on the progress and societal impacts of AI have been featured in multiple national and international media outlets.

Topics of Interest

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

  • Planning directly with pre-trained or fine-tuned LMs.
  • Planning for LMs.
  • LMs for (partial) model elicitation.
  • LMs for generating structured planning problem descriptions.
  • LMs for search guidance or search pruning.
  • LMs for validation and verification of plans, policies, or models.
  • LMs for generalization in planning and generalized planning.
  • Using LMs as a proxy for user preferences.
  • Using LMs to develop interfaces for planning-based systems or planning-related problems.
  • Other applications of LMs in planning.

Important Dates

Paper submission deadline: TBA
Paper acceptance notification: TBA

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 ICML style. 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 ICML conference to the workshop.

Paper submissions portal: TBA

Program Committee

To be announced.

Organizing Committee

  • Michael Katz, IBM contact
  • Augusto B. Corrêa, University of Oxford contact
  • Nir Lipovetzky, University of Melbourne
  • Sarath Sreedharan, Colorado State University
  • Katharina Stein, Saarland University
  • Luckeciano C. Melo, University of Oxford
  • Elliot Gestrin, Linköping University

Please send your inquiries to llmforplanning@gmail.com