Programs

3rd Workshop on Planning in the Era of LLMs (LM4Plan @ ICAPS 2026) Update: Invited talk slides and recording are now available! Visit https://llmforplanning.github.io/ for up-to-date information. The workshop will take place on June 29, 2026. 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.

Workshop on Planning and Reasoning about Beliefs, Goals and Intentions (PR-BGI) ICAPS 2026 Workshop Dublin, Ireland June 28, 2026 Program Time Session 14:30–14:34 Opening remarks 14:34–15:24 Invited talk: Implicitly Coordinating Agents Thomas Bolander 15:24–15:36 SMT-Based Goal and Plan Recognition Kin Max Piamolini Gusmão, Joan Espasa, Miquel Ramirez, Mustafa Faisal Zaki Abdelwahed, Nir Lipovetzky, Felipe Meneguzzi 15:36–15:48 Divergence Identities for Probabilistic Goal Recognition Giacomo Rosa, Nir Lipovetzky, Jean Honorio, Sebastian Sardina 15:48–16:00 Generation of Suspicious Behaviour

Workshop on Bridging the Gap Between AI Planning and (Reinforcement) Learning (PRL) Aim and Scope While AI Planning and Reinforcement Learning communities focus on similar sequential decision-making problems, these communities remain somewhat unaware of each other on specific problems, techniques, methodologies, and evaluations. This workshop aims to encourage discussion and collaboration between researchers in the fields of AI planning and (reinforcement) learning. We aim to bridge the gap between the two communities, facilitate the discussion of differences and similarities in existing techniques, and encourage collaboration across the fields.

Workshop on Reliability In Planning and Learning (RIPL; joint with HSRL) Aim and Scope of the Workshop Learning is the dominating trend in AI at this time, achieving (among others) unprecedented versatility and scalability in many forms of sequential decision making. Given the opaque nature of ML models and the lack of inherent guarantees, reliability is a key concern, prominently including safety, robustness, and fairness in various forms, but possibly other concerns as well.

Workshop on Roles of Planning in Games (RPG) ICAPS 2026 Workshop Dublin, Ireland June 28, 2026 RPG Website Aim and Scope of the Workshop Games and virtual environments have long served as test beds for Artificial Intelligence (AI), providing research challenges and benchmarks for assessment of intelligent systems performance. The specific application of Automated Planning and Scheduling (APS) technologies in games has been gaining popularity for uses both within the gameplay experience and for designing them.

Tutorial Program Overview Here is the list of the tutorials accepted to ICAPS 2026 Acronym Tutorial Title Ontology Planning Ontology Deepxube A Hands-on Deepxube Tutorial L2P Language-to-Plan

Workshop Program Overview Here is the list of the worskhops accepted to ICAPS 2026 Acronym Workshop Title CASP:ER Constraint And Satisfiability-based Planning GenPlan Generalization in Planning HAXP Human-Aware and Explainable Planning HPlan Hierarchical Planning HSDIP Heuristics and Search for Domain-independent Planning KEPS Knowledge Engineering for Planning and Scheduling LM4Plan Planning in the Era of Large Language Models PlanRob Planning and Robotics PR-BGI Planning and Reasoning about Beliefs, Goals and Intentions

ICAPS 2026 Outstanding Paper Awards The following papers were recognized with awards at ICAPS 2026. Best Paper Award Kai Xi, Stephen Gould and Sylvie Thiebaux Learning Lifted Action Models from Unsupervised Visual Traces Best Paper Runner-Up Award Augusto B. Corrêa, Simon Dold and Malte Helmert Potential Heuristics as Real-Valued Multilinear Polynomials Best Student Paper Award Pascal Lauer, Yifan Zhang, Patrik Haslum and Pascal Bercher I Always Told My Mom That Order Is Overrated: Unordered HTN Planning is in PSPACE and Models Problems Beyond STRIPS

ICAPS 2026 System Demonstrations An Open-Source Framework for Closed-Loop Multi-UAV Planning and Execution (pdf) Multi-Unmanned Aerial Vehicle (UAV) systems are increasingly used in applications such as Search and Rescue (SAR) and surveillance, where multiple aerial robots must coordinate under time pressure. As fleet sizes grow, manual coordination becomes infeasible, making automated planning essential to generate and adapt coordinated actions in dynamic environments. We present AUSPEX, an open-source framework for automated planning and execution in multi-UAV systems.