A unified, time-aligned schedule of all 12 workshops held on the two workshop days of ICAPS 2026 (Dublin, Ireland). The workshops run in parallel rooms, so this page lets you see, for any time slot, what is happening in each workshop. It is compiled from the workshops overview, the official timed schedule and the individual workshop pages (some of which link to external workshop websites).

⚠️ Always check the official pages before you go. This is an unofficial, hand-compiled overview that may contain mistakes and can fall out of date at any moment. Programmes, times and rooms change — sometimes on the day itself. For accurate, up-to-date information, rely on the official ICAPS 2026 schedule and the individual workshop pages linked below, not on this page.

Last compiled: 28 June 2026, 22:16 IST from the official ICAPS schedule and the individual workshop pages. Some programs are still marked draft/“to be announced” by the organizers — those entries are flagged below. Where the organizers publish only session blocks rather than per-talk slots, individual start times are evenly estimated from the session window and prefixed with a tilde (~) to mark them as approximate.

Workshop acronyms. 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 · PRL — Bridging the Gap Between AI Planning and (Reinforcement) Learning · RIPL — Reliability In Planning and Learning · RPG — Roles of Planning in Games.
Show workshops:
Day 1 (Sun):
Day 2 (Mon):

Day 1 — Sunday, June 28, 2026

Full-day workshops: GenPlan (Room 6), HAXP (Room 3), KEPS (Room 9), PRL (Room 1+2). Afternoon-only: RPG (Room 5), PR-BGI (Room 7). Morning sessions 09:00–12:30 · Lunch 13:00–14:30 · Afternoon sessions 14:30–18:00. Each half-day is split below into a slot before and a slot after the coffee break.

09:00 – 10:30 — Morning, before coffee break

Workshop / roomProgramme
GenPlan
Room 6 · full day		 Session 1 · Learning Planning Models from Demonstration & Perception:
  • 9:00 Keynote: Tom Silver (Princeton University)
  • 9:30 Learning Lifted Symbolic Planning Domains from Image Sequences (VISA) — Ulzhalgas Rakhman, Paul Schulte, Hector Geffner
  • 9:50 Learning HTNs from Visual Demonstration with VLMs — Ngoc La, Karthik Mahadevan, Pulkit Verma, Julie Shah
  • 10:10 Learning Bilevel Policies from Demonstrations for Long-Horizon Planning — Dillon Z. Chen, Till Hofmann, Toryn Q. Klassen, Sheila A. McIlraith
HAXP
Room 3
  • 9:00 Welcome & Opening Remarks
  • 9:15 Keynote 1: Mohan Sridharan (University of Edinburgh) — Explainable Reasoning and Learning in Ad hoc Teamwork
KEPS
Room 9
  • 09:00 Workshop Introduction
  • 09:10 Session 1 · Knowledge Acquisition & Domain Learning (per-talk times approximate):
    • ~09:10 Are We There Yet? Bridging the Knowledge Acquisition Gap in Automated Planning — R. Barták, L. Chrpa, S. Ondrčková, K. Pantůčková
    • ~09:23 Automatically Uncovering Intended Domain Constraints in Automated Planning — Elliot Gestrin, Johannes Fichte, Jendrik Seipp
    • ~09:36 Predicting Macro-Learning Performance Using Structural Regularity — Anton Gustafsson, Jendrik Seipp, Elliot Gestrin
    • ~09:49 JUS: Extending SIFT to Learn Planning Domains from Justified Plans — A. Lodemann, M. Ventura, G. Behnke, B. Glimm
    • ~10:02 On the Use of Large Language Models as Domain Model Configurators — Ilche Georgievski, Daniel Elis, Mauro Vallati
    • ~10:15 Offline Learning of Planning Domains with Subsymbolic Predicates Invention — Leonardo Lamanna
PRL
Room 1+2 · full day		 PRL’s coffee break runs 10:35–11:05 (slightly offset from the ICAPS-wide 10:30–10:50).
  • 9:00 Opening Remarks
  • 9:05 Session I:
    • ~9:05 Reinforcement Learning for Long-Horizon Unordered Tasks: From Boolean to Coupled Reward Machines — Kristina Levina, Nikolaos Pappas, Athanasios Karapantelakis, Aneta Vulgarakis Feljan, Jendrik Seipp
    • ~9:20 PBRMS: Priority-Based Reward-Machine Switching for Context-Aware Reinforcement Learning in Non-Stationary POMDPs — Andy Edmondson, Ron Petrick
    • ~9:35 Differentiable Learning of Lifted Action Schemas for Classical Planning — Jonas Reiter, Jakob Elias Gebler, Hector Geffner
    • ~9:50 Model-Driven Policy Optimization in Differentiable Simulators via Stochastic Exploration — Yuval Aroosh, Ayal Taitler
    • ~10:05 An Admissible Neuro-Symbolic Landmark Cut Heuristic – Preliminary Results — Magnus Cunow, Nicola J. Müller, Timo P. Gros, Gregor Behnke, Daniel Höller
    • ~10:20 Learning Lifted Action Models from Traces with Minimal Information About Actions and States — Jonas Gösgens, Niklas Jansen, Hector Geffner

10:30 – 10:50 — Coffee break

10:50 – 12:30 — Morning, after coffee break

Workshop / roomProgramme
GenPlan
Room 6 · full day		 Session 2 · Learning General Policies:
  • 10:50 Keynote: Anders Jonsson (Universitat Pompeu Fabra)
  • 11:20 Efficient Lookahead Encoding and Abstracted Width for General Policies — Michael Aichmüller, Simon Ståhlberg, Martin Funkquist, Hector Geffner
  • 11:40 Learning Symbolic Policies from GNNs — Martin Funkquist, Simon Ståhlberg, Hector Geffner
  • 12:00 Learning General Policies for Partially Observable Deterministic Planning — Samridhi Kalra, Till Hofmann, Hector Geffner
  • 12:20 Enhancing Generalisation in GPT-Based Planning Policies — Massimiliano Tummolo, Nicholas Rossetti, Ivan Serina, Alfonso Gerevini
  • 12:40 CoSP-TL: Common-Sense Planning under Temporal Logic Constraints with LLMs — Emanuele Musumeci, Alessio Saladino, Elena Umili, Luca Iocchi, Daniele Nardi
HAXP
Room 3
  • 10:50 Paper Session 1 (per-talk times approximate):
    • ~10:50 Generalized Execution for Dialogue Planning — Victoria Armstrong, Christian Muise
    • ~11:10 Iterative Planning with MUGS Explanations: Exploring the Design Space — J. Schmalz, D. Groß, R. Eifler, J. Méndez, R. Dachselt, S. Gumhold, J. Hoffmann
    • ~11:30 Generating Explainable Counterfactual Policies through Temporal Logic Queries — Arnaud Lequen, Clément Legrand-Lixon, Léo Saulières
    • ~11:50 Constraint based Plan Distance Metric for Operator-Centric Replanning in Multi-Agent Progression Missions — E. Siboulet, A. Bit-Monnot, M.-E. Coupvent des Graviers, C. Guettier
    • ~12:10 Explaining Symbolic Action Policies using Facet Reasoning — Jennifer Santos, Johannes K. Fichte, Daniel Gnad
KEPS
Room 9		 KEPS Session 2 runs until 12:40, slightly past the block.
  • 10:50 Session 2 · Classical, Numeric & Uncertain Planning (per-talk times approximate):
    • ~10:50 Planning while Learning with Anytime Sound and Complete Models — P. Copete, D. Aineto, E. Onaindia, E. Scala
    • ~11:04 Planning with Uncertain Action Models — F. Percassi, A. Saetti, E. Scala
    • ~11:18 Automated Planning with Incomplete Open World Models — Mikhail Soutchanski
    • ~11:32 Configuring Lifted Initial States for Classical Planning — A. Gragera, R. Fuentetaja, Á. García-Olaya
    • ~11:46 Incremental Planning over Lifted Abstractions — M. Kornherr, D. Gnad, Z. G. Saribatur, J. K. Fichte
    • ~12:00 Planning Task Shielding: Detecting and Repairing Flaws in Planning Tasks through Turning them Unsolvable — A. Pozanco, M. Morales, P. Totis, D. Borrajo
    • ~12:14 Optimal Parity Resolution in Difference Models via Numeric Planning — L. Bonassi, J. Wilson, R. Chang, K. Fine, N. Hawes
    • ~12:28 Semantic Mediation: An LLM-Based Approach for Ground Truth in Human-in-the-Loop Automated Planning in Supply Chain Networks — Ryan Farish, Emanuele De Pellegrin, Ron Petrick
PRL
Room 1+2 · full day		 PRL’s coffee break runs 10:35–11:05 (slightly offset from the ICAPS-wide 10:30–10:50).
  • 11:05 Keynote: Ivan Serina & Alfonso E. Gerevini — On Learning Planning Heuristics and General Policies through GNNs and Transformers
  • 12:00 Session II:
    • ~12:00 Symmetry-Aware Transformer Training for Automated Planning — Markus Fritzsche, Elliot Gestrin, Jendrik Seipp
    • ~12:15 Effective Reinforcement Learning Exploration in Stochastic Shortest Paths with Dead-Ends — Gustavo De Mari Pereira, Leliane N. de Barros
    • ~12:30 On the Possibility of Solving STRIPS Planning Problems with REINFORCE — S. T. Lin
    • ~12:45 Using a Search-Based Safety Oracle for RL Policy Fine-Tuning — S. T. Lin, Nicola J. Müller, Tim Nico Bauerschmidt, Chaahat Jain, Jörg Hoffmann, Isabel Valera

13:00 – 14:30 — Lunch (Sussex Restaurant)

14:30 – 16:00 — Afternoon, before coffee break

Workshop / roomProgramme
GenPlan
Room 6 · full day		 Session 3 · Abstraction, Skills & Transfer in RL:
  • 14:30 Keynote: David Abel (Google DeepMind & University of Edinburgh)
  • 15:00 Going Beyond State-Reaching: Abstractions for Intrinsically Motivated Skill Discovery — Akhil Bagaria, Anita De Mello Koch, George Konidaris
  • 15:20 Structural Analogies as Posterior Transfer in Continual RL — Sole Traverso, Joshua Benjamin Evans, Henning Sprekeler, Marc Toussaint
  • 15:40 Autonomous Assessment of Generalizability of AI Agent Capabilities — Daniel Richard Bramblett, Rushang Karia, Adrian Ciotinga, Pulkit Verma, YooJung Choi, Siddharth Srivastava
HAXP
Room 3
  • 14:30 Keynote 2: Mark Keane — When Explanations Need Explanation: The Case of the Semi-Factual
  • 15:35 Paper Session 2: An Epistemic Human-Aware Task Planner Integrating Agents Expectations — Gabriele Sartor, Rachid Alami
KEPS
Room 9
  • 14:30 Session 3 · Scheduling & Planning Applications (per-talk times approximate):
    • ~14:30 Extracting Structural Knowledge from Precedence-Induced Betweenness Patterns in Scheduling Problems — I. Català, C. Pérez, M. A. Salido
    • ~14:45 The Role of Knowledge Engineering within a Fielded Planning Application — L. McCluskey, A. Lindsay, M. Vallati, K. McCabe
    • ~15:00 Distribution Network Transition Problem: A Planning Knowledge Model Capturing Structural Constraints — F. Percassi, S. Castellanos-Paez, M. Vallati, M.-C. Alvarez-Hérault
    • ~15:15 On the Use of AI Planning for Water Management of the Red River Basin in Vietnam — D. Aineto, N. Bettinzoli, Ngo Le An, E. Scala, I. Serina
    • ~15:30 Modeling Challenges in Procedure Synthesis for Earth Independent Anomaly Response — J. Benton, I. Kostitsyna, R. Levinson, A. Paredes
    • ~15:45 Medical Procedure Tracking using Abductive Planning — A PARADIGM Shift — M. Wessel, M. Cogswell, J. Tyan, B. Price
PRL
Room 1+2 · full day		 PRL’s afternoon coffee break runs 16:00–16:30.
  • 14:30 Keynote: Jörg Hoffmann & Chaahat Jain — Automatic Safety Debugging of Tree-Ensemble Action Policies in AI Planning
  • 15:25 Session III:
    • ~15:25 Synthesis of Shields for Safe Reinforcement Learning in Both Discrete and Continuous State and Action Spaces — Srinivas Nedunuri, Douglas Cale Crowder
    • ~15:37 Towards Symbolic Planning via Diffusion — Arman Mohammadi, Markus Fritzsche, Jendrik Seipp
    • ~15:49 The DeepXube Software Package for Solving Pathfinding Problems with Learned Heuristic Functions and Search — Forest Agostinelli
RPG
Room 5 · PM only
  • 14:30 Welcome
  • 14:35 Invited Talk: Rogelio Cardona-Rivera (University of Utah) — Planning for the Design of Experiences
  • 15:20 Papers (Planning-based Tools for Games):
    • 15:20 From Domain to Action: A Cohesive Planning Pipeline for Game AI in Unity Engine — Marek Marchlewicz
    • 15:40 Dynamic Scene Reconstruction for Prototyping Planning-Based Game Environments — A. Othman, E. De Pellegrin, R. Petrick
PR-BGI
Room 7 · PM only		 A remote Zoom session is also available.
  • 14:30 Opening remarks
  • 14:34 Invited Talk: Thomas Bolander (DTU) — Implicitly Coordinating Agents
  • 15:24 SMT-Based Goal and Plan Recognition — K. M. P. Gusmão, J. Espasa, M. Ramirez, M. F. Z. Abdelwahed, N. Lipovetzky, F. Meneguzzi
  • 15:36 Divergence Identities for Probabilistic Goal Recognition — G. Rosa, N. Lipovetzky, J. Honorio, S. Sardina
  • 15:48 Generation of Suspicious Behaviour — P. Masters, D. Gallagher, G. A. Kaminka, M. Vered

16:00 – 16:20 — Coffee break

16:20 – 18:00 — Afternoon, after coffee break

Workshop / roomProgramme
GenPlan
Room 6 · full day		 Session 4 · Symbolic Reasoning, Abstraction & Verification:
  • 16:20 Revisiting Landmarks: Generalizing over Problem Instances — Issa Hanou, Sebastijan Dumancic, Mathijs de Weerdt
  • 16:40 Abstraction via Skolemization for Generalized Planning — Till Hofmann, Dillon Z. Chen, Toryn Q. Klassen, Sheila A. McIlraith
  • 17:00 Verifinsta: Verifying If an Instance Belongs to a Domain — Claudia Grundke, Gabriele Röger, Malte Helmert
  • 17:20 Efficient Search by Tentatively Pruning Objects from Planning Tasks — Anita De Mello Koch, Naman Shah, Cameron Allen, George Konidaris
  • 17:40 Logical Regression for Planning with Axioms — Connor Little, Christian Muise
HAXP
Room 3
  • 16:20 Paper Session 2 (cont.) (per-talk times approximate):
    • ~16:20 How Hard Is It to Lie in Model Reconciliation? — Huanghua Sheng, Pascal Bercher, Sarath Sreedharan
    • ~16:40 Can LLMs Explain Plans Well? — Philip D. Hopkins, Stylianos L. Vasileiou, Sarath Sreedharan
    • ~17:00 Do You Even Know What I Want? Improving LLMs Ability to Detect Hidden User Intent — Kelsey Sikes, Sarath Sreedharan
  • 17:20 Fishbowl Discussion (until 18:00)
KEPS
Room 9
  • 16:20 Session 4 · Robotics & Multi-agent Planning (per-talk times approximate):
    • ~16:20 When Can Planning Benefit from Common-Sense Knowledge? — M. Armony, A. Meroño-Peñuela, G. Canal
    • ~16:33 Dynamic Scene Reconstruction for Planning Environments — A. Othman, P. Singh, E. De Pellegrin, M. Koskinopoulou, R. Petrick
    • ~16:46 OOMPA 2025.08: A First Cut of the Toolkit for Object-Oriented Modeling for Planning and Acting — M. Roberts, D. Chan, D. Nau, J. Macbeth
    • ~16:59 Structuring World State Knowledge for Multi-UAV Automated Planning — Kai Sommer, Jane Jean Kiam
    • ~17:12 maPO: An Ontology for Multi-Agent Path Finding and Its Usage for Explaining Planner Behaviour — B. Muppasani, R. Dey, B. Srivastava, V. Narayanan
  • 17:25 Closing (until 17:30)
PRL
Room 1+2 · full day		 PRL’s afternoon coffee break runs 16:00–16:30.
  • 16:30 Session IV:
    • ~16:30 Pareto Q-Learning with Reward Machines — Arnaud Lequen, Clément Legrand-Lixon, Léo Saulières
    • ~16:45 MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning — Yusuf Syed, Viraj Parimi, Brian C. Williams
    • ~17:00 Data Efficient Training of Heuristic Functions for Satisficing Search — Forest Agostinelli, Shahaf S. Shperberg
    • ~17:15 Heuristic Learning and Search Without Exhaustive Action Enumeration — Misagh Soltani, Forest Agostinelli
  • 17:30 Closing Remarks
RPG
Room 5 · PM only
  • 16:20 Papers (Applications of Games for Planning):
    • 16:20 Baba Is Axioms: A Challenging Benchmark for Classical Planning with Axioms — R. Rochwerg, A. Fletcher, S. Papais, C. Wang, C. Little, T. Hu, C. Muise
    • 16:35 A Good Snowman Is (also Numerically) Hard to Plan — M. Paparo, F. Doria, M. Maratea, M. Vallati
    • 16:50 Active Information Gathering in Social Deduction Games — Haochong Luo, Chenyuan Zhang, Guang Hu
  • 17:10 Invited Talk: Jeff Orkin (Bitpart AI) — Planning in Games in the Age of LLMs
  • 17:55 Closing (until 18:00)
PR-BGI
Room 7 · PM only
  • 16:20 IPC competition session
  • 16:35 Concurrent Action Models for DEL — Ludovico Deponte
  • 16:47 RP-M*P: Extending Epistemic Planning with Dynamic Desires and Intentions — R. L. De Venezia, C. Muise
  • 16:59 ALETHEIA: Adaptive Epistemic Planning over Kripke Models with DEL Product-Update Semantics — Haniel U. Vasquez Morales
  • 17:11 Epistemic Ambiguity Is a Design Problem: Toward Complete Online Planning with Verified Actions — Halim Djerroud
  • 17:23 Synthesis Under Multi-Agent Environment Assumptions for Specifications in LTL on Finite Traces — S. Condrò, G. De Giacomo, G. Parretti, E. Santini
  • 17:35 Synthesis Foundations for Online LTLf Goal Management — G. De Giacomo, Y. Lesperance, G. Parretti, F. Patrizi
  • 17:47 Hardness of MAPF under Destination Uncertainty — P. Maurice Dekker
  • 17:59 Closing remarks

Day 2 — Monday, June 29, 2026

Full-day workshops: LM4Plan (Room 1+2), PlanRob (Room 9), HSDIP (Room 7), RIPL (Room 6). Afternoon-only: CASP:ER (Room 3), HPlan (Room 5). Morning sessions 09:00–12:30 · Lunch 12:30–14:00 · Afternoon sessions 14:00–17:30. Each half-day is split below into a slot before and a slot after the coffee break.

09:00 – 10:30 — Morning, before coffee break

Workshop / roomProgramme
LM4Plan
Room 1+2 · full day
  • 9:00 Opening remarks
  • 9:05 Semantic Partial Grounding via LLMs — G. Canonaco, A. Pozanco, D. Borrajo
  • 9:20 Benchmarking LLM Pipelines for Natural Language to Automated Planning Models — M. Tantakoun, C. Muise, X. Zhu
  • 9:35 Operationally Grounded Evaluation and Repair for NL-to-PDDL Problem Generation — J. Rosa, B. Martins, L. M. Silveira, P. R. L. dos Santos
  • 9:50 Towards LLM-Driven Synthesis of Narrative Planning Models — A. Fletcher, C. Muise
  • 10:05 A Natural Language Copilot for Interactive Plan Space Exploration — Paul Horn, Daniel Gnad
PlanRob
Room 9 · full day
  • 09:00 Workshop Introduction
  • 09:10 Keynote: Nick Hawes (Univ. of Oxford) — Long-Range Underwater Glider Planning Under Uncertainty
  • 10:10 Rob-LAPIS: Grounding Verbal Household Robot Instructions via Iterative PDDL Synthesis — E. Musumeci, A. H. Drid, D. Nardi
HSDIP
Room 7 · full day
  • 9:00 Introduction
  • 9:05 A* with h^max Definitely Finds Optimal Plans — Formally Verifying a Planner Based on Heuristic Search — G. Behnke, S. Kilian, M. Gattinger
  • 9:20 Eager vs. Lazy Duplicate Detection in A* — Yuki Suzuki, Alex Fukunaga
  • 9:35 Base Strategy Still Matters: Triangle Search in Domain-Independent Planning — J. Thayer, S. Lemons, J. Seipp
  • 9:50 Compact Representatives of Potential Heuristics — Simon Dold, Malte Helmert
  • 10:00 Delete Relaxation with Axioms — T. R. Petit, S. Dold, D. Speck, M. Helmert
  • 10:15 GONDOR to the Rescue: Satisficing Planning with Low Memory — Y. Vernik, A. Tuisov, A. Shleyfman
RIPL
Room 6 · full day		 Technical talks are 15 min + 5 min discussion.
  • 9:00 Welcome & Opening Remarks
  • 9:00 Invited Talk: Siddharth Srivastava — The Return of Structure: Learning Symbolic World Models from Raw Data for Reliable Planning and RL
  • 10:00 Session · Multi-Agent Coordination under Uncertainty: Social Laws for Multi-agent Coordination in Stochastic Environments — R. Fernandez, C. Probine, T. Lee, J. Chen, E. Karpas, M. A. Rahman, P. Stone, U. Topcu

10:30 – 10:50 — Coffee break

10:50 – 12:30 — Morning, after coffee break

Workshop / roomProgramme
LM4Plan
Room 1+2 · full day
  • 10:50 FABLE: A Novel Data-Flow Analysis Benchmark on Procedural Text for LLM Evaluation — V. Pallagani, N. Gupta, J. A. Aydin, B. Srivastava
  • 11:05 ALPSBench: Can Large Language Models Reason Their Way Through Planning Formalisms? — M. Tantakoun, C. Muise, X. Zhu
  • 11:20 On the Ability of Transformers to Verify Plans — Y. Sarrof, Y. Du, K. Stein, A. Koller, S. Thiebaux, M. Hahn
  • 11:35 Toward a General Framework for Evaluating Per-Domain Generalization Using LLMs, Theorem Provers, and Statistical Model Checking — N. J. Müller, N. Rudolph, A. Taitler, T. P. Gros
  • 11:50 Integrating the Unified Planning Framework via MCP with LLMs for Reliable Automated Planning — J. Areias Saraiva, T. Kirste
  • 12:05 Learning HTNs from Visual Demonstration with Vision-Language Models: Preliminary Results — N. La, K. Mahadevan, P. Verma, J. Shah
PlanRob
Room 9 · full day
  • 10:50 Data-Driven Metareasoning in Search in Infinite Completion Trees for TAMP — E. Tadmor, E. Karpas, M. Toussaint
  • 11:05 From Kinematics to Dynamics: Learning to Refine Hybrid Plans for Physically Feasible Execution — L. Erez, S. Shperberg, A. Taitler
  • 11:20 Sampling-based Task and Kinodynamic Motion Planning under Semantic Uncertainty — Q. H. Ho, Z. Sunberg, M. Lahijanian
  • 11:35 [Title to be announced] — B. Döschl, J. Olkin, P. Jamakatel, B. Williams, J. J. Kiam
  • 11:50 Robust Visual Planning under Partial Observability and Perceptual Uncertainty — G. Azran, M. Navat, S. Keren
  • 12:05 Using Automated Planning for the Safety Protocol Verification of Space Robotics — S. Papais, C. Muise
  • 12:20 Discussion
HSDIP
Room 7 · full day
RIPL
Room 6 · full day		 Technical talks are 15 min + 5 min discussion.
  • 10:50 Session · Neuro-Symbolic Policies and Their Verification:
    • ~10:50 Safety Verification of Additive Tree Ensemble Policies via Symbolic Search — M. Schubert, D. Höller
    • ~11:10 A Comparison of Sampling Strategies for Learning Policies — F. Musayev, D. Drexler, D. Gnad, J. Seipp
    • ~11:30 Formula Neural Networks as Action Policies in Safety-Critical Planning: An Empirical Evaluation — V. S. Putrich, T. N. Bauerschmidt, C. Jain, S. Lin, J. Hoffmann, I. Valera
    • ~11:50 Prompt, Prove, Patch: The Neuro-Symbolic Loop for General Policy Synthesis — D. Drexler, M. Fritzsche, F. Musayev, S. Ståhlberg

12:30 – 14:00 — Lunch (Sussex Restaurant)

14:00 – 15:30 — Afternoon, before coffee break

Workshop / roomProgramme
LM4Plan
Room 1+2 · full day
  • 14:00 LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning — Elliot Gestrin, Jendrik Seipp
  • 14:15 Personalized Medication Planning via Direct Domain Modeling and LLM-Generated Heuristics — Y. Vernik, D. Izhaki, A. Tuisov, H. Weitman, A. Shleyfman, G. Kaminka
  • 14:30 Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents — S. Sohrabi, H. Ananthakrishnan, H. Kokel, K. Srinivas, M. Katz
  • 14:45 The Curious Case of Planning for Unreliable Agents: Challenges and Opportunities in Orchestrating Generative AI Agents — R. Daneshi, S. Patra, K. Dwarakanath, S. Gopalakrishnan, D. Borrajo, S. Sreedharan
  • 15:00 Think Hierarchically, Act Optimally: Decoupled Hierarchical Planning and Execution for LLM Agents — V. Kumar, J. Khatri, S. Karande
PlanRob
Room 9 · full day
  • 14:00 Keynote: Steve Chien (NASA JPL) — Trusted AI on Mars
  • 15:00 Inverse Manipulation through Symbolic Planning and Residual Operator Learning — Y. Yildirim, G. Rauso, R. Caccavale, A. Finzi
  • 15:15 Situated Planning with Soft Goals — A. Coles, E. Karpas, S. Shperberg, S. E. Shimony, W. Ruml
HSDIP
Room 7 · full day		 Talk length: L = long (12+3 min), S = short (8+2 min).
  • 14:00 When Local Plans Cannot Be Global: A Sheaf-Theoretic View of Decomposition in Numeric Planning — Jiajia Song, Guang Hu (L)
  • 14:15 On the Optimality of Numeric Planning with Control Variables — Á. Aso-Mollar, D. Aineto, E. Scala, E. Onaindia (L)
  • 14:30 A Notion of Width for Numeric Planning Problems — G. Rosa, N. Lipovetzky, J. Honorio, S. Sardina, E. Scala (L)
  • 14:45 Domain-Abstraction Heuristics for Simple Numeric Planning — M. Fritzsche, M. Gruntov, A. Shleyfman, D. Gnad (S)
  • 14:55 Counting Plans with Heuristic State-Space Search — David Speck (S)
  • 15:05 Make Yourself Special: Qualified Dominance Task Reformulation For Optimal Planning — R. Tollund, Á. Torralba (L)
RIPL
Room 6 · full day
  • 14:00 Session · Learning for Classical Planning:
    • ~14:00 Self-Supervised Improvement of Learned Search Guidance — M. Hao, S. Thiebaux, F. Trevizan
    • ~14:20 Learning Interpretable Classifiers for PDDL Planning — Arnaud Lequen
    • ~14:40 Learning Object Priorities for Partial Grounding — M. Musavi, J. K. Fichte, D. Gnad
    • ~15:00 LLM-Evolved Pattern Generators for Optimal Classical Planning — W. Phung, A. Lequen, D. Drexler, J. Seipp
CASP:ER
Room 3 · PM only
  • 14:00 Opening remarks
  • 14:15 A Comparison of Unsolvability Certificates in Planning and Model Checking — Malte Helmert, Tanja Schindler
  • 14:30 Transforming and Encoding FTS for SAT Solving: What Helps, What Hurts — João Felipe, Álvaro Torralba, Gregor Behnke
  • 14:45 Lifted Planning as SMT — Miquel Bofill, Cristina Borralleras, Josu Oca
  • 15:00 An Automata-Based Constraint Programming Framework for Optimal Classical Planning — D. Van Meerbeeck, A. Lequen, G. Pesant, J. Seipp
  • 15:15 Towards Qualitative Constraint-Based HTN Planning: A Research Agenda — T. Schwartz, C. Walther, D. Wolter
HPlan
Room 5 · PM only
  • 14:00 Welcome
  • 14:05 Invited Talk: Lee McCluskey — Real-world AI Planning Applications need HTN: True or False? (incl. Q&A)
  • 15:05 Previously-published papers (discussion continuing into the break):
    • 15:06 Designing an Intelligent Do-It-Yourself (DIY) Assistant — Gregor Behnke
    • 15:14 On Trustworthy, Explainable, and Verifiable High-Level Autonomy via Hierarchical Planning — Roman Barták
    • 15:22 Probabilistic Hierarchical Goal Network Planning with UCT — David Chan

15:30 – 15:50 — Coffee break

15:50 – 17:30 — Afternoon, after coffee break

Workshop / roomProgramme
LM4Plan
Room 1+2 · full day
  • 15:50 Invited Talk: Jendrik Seipp — LLMs don't even need to plan — they can build planners
  • 16:40 Panel discussion & closing remarks (until 17:30)
PlanRob
Room 9 · full day
  • 15:50 EuroCore: Enabling Reproducible Planning and Robotics Workflows on the European AI-on-Demand Platform — P. Forte, U. Köckemann, A. Saffiotti
  • 16:05 AttrAP: a New Heuristic-Based Method to Solve Heterogeneous MRTA Problems Minimizing the Makespan — S. Ferrier, A. Renzaglia, O. Simonin
  • 16:20 Fixed-Haven Reservation for Online Multi-Agent Pickup and Delivery in Dense Warehouses — T. Hirayama, K. Yoshida, H. Sakaji, I. Noda
  • 16:35 Learning Interpretable Scheduling Policies for Online Multi-Robot Task Allocation via Inductive Logic Programming — M. I. Memon, U. Patil, I. Awaad, Y. M. Youssef
  • 16:50 Toward a Unified Framework for Dynamic Task Allocation and Adaptive Synergy in Hybrid Emergency Response Teams — G. Beraldo, A. Umbrico, A. Orlandini
  • 17:05 Closing remarks
HSDIP
Room 7 · full day		 Talk length: L = long (12+3 min), S = short (8+2 min).
  • 15:50 Bounded-Suboptimal Beam Search — D. W. Thomas, S. Wissow, M. Bauer, P. McAfee, W. Ruml (L)
  • 16:05 Computing Potential Heuristics Without Grounding PDDL Actions — P. Lauer, Á. Torralba, D. Fišer (L)
  • 16:20 A Comparison of Cost Partitioning Algorithms for Multiple Sequence Alignment — M. Skjelnes, D. Gnad, J. Seipp (L)
  • 16:35 Learning Admissible Heuristics via Cost Partitioning — H. Barral, Q. Cappart, M.-J. Huguet, S. Thiébaux (L)
  • 16:50 Automated Planning with Incomplete Open World Models — Mikhail Soutchanski (L)
  • 17:05 Discussion
  • 17:20 Closing remarks (until 17:30)
RIPL
Room 6 · full day
  • 15:50 Open Discussion & Closing Remarks (until 17:30)
CASP:ER
Room 3 · PM only
  • 15:50 Leveraging CP for Numeric-to-Classical Planning Compilations — C. Davesa Sureda, J. Espasa Arxer, I. Miguel, M. Villaret
  • 16:05 Planning and Scheduling, What’s the Difference Anyway? — Arthur Bit-Monnot
  • 16:20 An Insertion-Based Linked List Variable and Regular Constraint for Classical Planning with CP — Damien Van Meerbeeck
  • 16:35 CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling — V. Patel, A. Deodhar, D. Birru
  • 16:50 Guiding CP Search for Recurring Vehicle Routing Problems with Learned Heuristics — M.-E. Coupvent des Graviers, J. Turi, C. Guettier
  • 17:05 Learning Heuristics to Solve Routing Problems Increasingly Faster — M.-E. Coupvent des Graviers, J. Turi, C. Guettier
  • 17:20 Closing remarks
HPlan
Room 5 · PM only
  • 15:50 Accepted HPlan papers (8+2 min each):
    • 15:50 Beyond Validity: Qualitative Robustness of HTN Plans via Conceptual Neighborhoods — Tobias Schwartz
    • 15:58 Hierarchical Task Networks as Social Laws — Itay Bryt
    • 16:06 No Plan-Space? No Problem! Towards Makespan-Optimal HTN Planning via Progression Search — Harrison Oates
    • 16:14 Improved Automated Repair of Totally-Ordered Hierarchical Task Network Domains — Pascal Bercher
    • 16:22 Bounded Decomposition under Extreme Orderings in HTN Planning — Pascal Bercher
    • 16:30 Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding — Gaspard Quenard
    • 16:38 Lose the Order, Keep the Hierarchy: Deordering HTN Plans — Gaspard Quenard
    • 16:46 Learning HTNs from Visual Demonstration with Vision-Language Models: Preliminary Results — Ngoc La
    • 16:54 Three FOND HTN papers (LL(k) Decision Processes; Just as FOND; Fixed-Method FOND HTN Solver) — Harrison Oates
  • 17:30 End

Sources: ICAPS 2026 workshops overview and timed schedule; individual workshop pages and external workshop websites (GenPlan, KEPS, LM4Plan, PRL, RPG, HPlan). Programmes change; please confirm against the official ICAPS 2026 site.