Tutorial

Michael Katz is a Principal Research Scientist at IBM T.J. Watson Research Center. His research interests and expertise are both in theory of domain independent planning and in practice of building efficient tools for solving planning problems. Much of his research lays in the intersection of planning and reinforcement learning and planning and language models. He is a AAAI Senior Member. He was a program chair of ICAPS 2021 and currently serves as an ICAPS executive council board member and a Competition Liaison (second term). He received numerous awards for his research, including Influential Paper Award (test-of- time) in 2023 for his work on heuristic search for classical planning and Best Dissertation Award in 2011. His domain-independent planning solvers have won International Planning Competitions (IPC) in 2018 and in 2014.

He was a co-organizer of seven editions of the Heuristics and Search for Domain-independent Planning (HSDIP) workshops, as well as of five editions of the Bridging the Gap Between AI Planning and Reinforcement Learning (PRL) workshop, which he co-created in 2020. He is the creator and a workshop chair of the LM4Plan workshop series on Planning in the Era of LLMs (LM4Plan@AAAI, LM4Plan@ICAPS 2025). He was a panelist at workshops/bridge program at AAAI/ICAPS. He has given overview tutorials on AI Planning at AAAI/IJCAI, as well as a tutorial at ICAPS on Finding multiple plans for classical planning problems. He frequently serves as an AC/SPC for AAAI/IJCAI/ICAPS.

Harsha Kokel is a Research Scientist at IBM Research. Her work centers on automating sequential decision-making, with recent research focusing on planning for and with large language models. She earned her Ph.D. from The University of Texas at Dallas where her dissertation was recognized with the 2024 David Daniel Thesis Award. Her research has appeared in venues such as AAAI, NeurIPS, IJCAI, ICAPS, and ACS.

Harsha is serving as an Area Chair for NeurIPS 2025 and has been an active reviewer for numerous journals, conferences, and workshops, including AAAI, IJCAI, NeurIPS, SDM, and DMKD. From 2020 to 2023, she was an Assistant Electronic Publishing Editor for JAIR. She has also co-organized the Planning and Reinforcement Learning (PRL) Workshops at AAAI 2025, ICAPS 2023 and 2024, and IJCAI 2023. She recently organized PLAN-FM Bridge Program at AAAI to foster collaboration between the NLP, Planning, and Robotics communities. At this bridge she gave a tutorial on Benchmarks for Planning in Natural Language.

Christian Muise is an Assistant Professor in the School of Computing at Queen’s Univer- sity. Prior to joining Queen’s, he received his PhD from the University of Toronto, held postdoctoral positions with the University of Melbourne and MIT, and worked in industry as a research scientist with the MIT-IBM Watson AI Lab. Dr Muise is the author of over 100 scholarly works in the area of Artificial Intelligence (AI). His main area of focus is on the understanding and modelling of sequential decision-making problems, with a focus on settings where uncertainty plays a role. In 2022, Dr Muise was recognized with the ICAPS Influential Paper Award (test-of-time) for his work on non-deterministic planning, which remains the state-of-the-art approach for solving planning problems with uncertainty. He has also been recognized with several teaching awards, including the Howard Staveley Teaching Award and the Queen’s University Principal’s Educational Technology Award.

Dr Muise is a member of the Ingenuity Labs at Queen’s University, an active Scotiabank Scholar with the Scotiabank Centre for Customer Analytics, academic co-director of the Master’s in Digital Product Management, and a Faculty Affiliate with the Vector Institute for Artificial Intelligence. After serving as Program Chair for the International Conference of Automated Planning and Scheduling (ICAPS), he was elected to serve on the council for the ICAPS organization. Dr Muise also serves as an Editorial Board Member of the Artificial Intelligence Journal (AIJ).