Planning in the Era of Language Models

9:30–12:00,
December 2nd,
San Diego, CA, USA

Tutorial @ NeurIPS 2025

For over six decades, the field of automated planning has been at the heart of AI, empowering intelligent systems to reason, act, and achieve goals in complex, dynamic environments. From robotics and logistics to space exploration, planning research has fueled autonomous decision-making in real-world applications.

Today, as large language models redefine what’s possible in AI, the principles and methodologies of planning are more vital than ever. The planning community brings decades of experience in designing, benchmarking, and interpreting intelligent behavior; expertise that can accelerate the development of powerful, trustworthy, and general-purpose LLM-based agents.

Participants will gain a clear understanding of what planning truly entails, what has been learned (and sometimes forgotten) in the shift toward LLM-based approaches, and how foundational insights from the planning community can inform the creation of stronger, more reliable, and more scalable LLM-powered planners.

Program

What is Planning?

What kind of planning problem do I have aka Planning Formalisms? What kind of solutions am I looking for aka Computational Problems? How can I describe my planning problem aka Planning Languages?

30 mins
Solving Planning Problems

Pre-LLM era Early LLM era Modern LLM era

30 mins
Tools to learn and work with planning models

Natural language to PDDL (L2P) Time series data to PDDL (MACQ) Planning tools you can use to build, solve, and analyze models

30 mins
Evaluating core reasoning for reliable planning tasks

Designing an experimental evaluation of a planner Evaluating other planning-related capabilities (e.g. applicable actions, plan validation, goal recognition) Range of datasets available for evaluationss

30 mins
Panel: LMs for Sound and Efficient Planning: Limitations and Opportunities
Moderated by Christian Muise
30 mins

Panelist

Noam Brown

Open AI

Noam Brown is a research scientist at OpenAI investigating reasoning and multi-agent AI. He co-created Libratus and Pluribus, the first AIs to defeat top humans in two-player no-limit poker and multiplayer no-limit poker, respectively, and Cicero, the first AI to achieve human-level performance in the natural language strategy game Diplomacy. He has received the Marvin Minsky Medal for Outstanding Achievements in AI, was named one of MIT Tech Review’s 35 Innovators Under 35, and his work on Pluribus was named by Science as one of the top 10 scientific breakthroughs of 2019. Noam received his PhD from Carnegie Mellon University.

Subbarao Kambhampati

Arizona State University

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 Association for the Advancement of Artificial Intelligence, American Association for the Advancement of Science, and Association for Computing machinery, and a recent recipient of the AAAI Patrick H. Winston Outstanding Educator award. He served as the president of the Association for the Advancement of Artificial Intelligence, a trustee of the International Joint Conference on Artificial Intelligence, the chair of AAAS Section T (Information, Communication and Computation), 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. He can be followed on Twitter @rao2z.