PRL Workshop Series

Bridging the Gap Between AI Planning and Reinforcement Learning

Joint Workshop on Planning for Complex Real-World Applications (CAIPI) and Bridging the Gap Between AI Planning and (Reinforcement) Learning (PRL)

IJCAI’26 Bremen, Germany
Date: August 15 - 17, 2026
prl.theworkshop@gmail.com \

Aim and Scope

Symbolic planning, Reinforcement Learning, and emerging directions such as LLMs for planning and Neuro-Symbolic approaches all contribute important theoretical and applied perspectives on sequential decision-making. However, these communities often evolve in parallel, with distinct assumptions, theoretical backbones, methods, benchmarks, and forms of evaluation. As a result, progress on planning is fragmented across community boundaries, despite a shared interest in solving complex decision-making problems.

This joint workshop aims to bring these communities together across both dimensions of the field: theoretical foundations and applications. It provides a platform for researchers working on symbolic, learning-based, and hybrid planning approaches to discuss common challenges, compare methodologies, and identify opportunities for integration. By fostering exchange across established and emerging research directions, the workshop seeks to strengthen connections within the broader planning community and support the development of more general and practically relevant planning approaches.

Topics of Interest

We invite submissions at the intersection of AI Planning and (Reinforcement) Learning for theoretical and applied problems. The topics of interest include, but are not limited to, the following

Important Dates

IJCAI will be in-person this year. Authors of accepted workshop papers are expected to physically attend the conference and present in person.

Program

Time Title Authors
9:00 Opening Remarks  
9:10 Dynamic Haven Selection for Multi-Agent Pickup and Delivery in Constrained Warehouses Taisei Hirayama, Kohei Yoshida, Hiroki Sakaji, Itsuki Noda
9:30 Modelling Choices in Neurosymbolic Action Model Learning from Visual Traces Adem Kikaj, Lennert De Smet, Giuseppe Marra, Luc De Raedt
9:50 ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability Juarez Monteiro, Nathan Gavenski, Guilherme Drummond Lima, Francisco Galuppo Azevedo, Odinaldo Rodrigues, Adriano Veloso
10:10 Discrete Vision Tokens and Temporal Transformers for City-Scale Crowd Flow Prediction Antoni Zięciak, Michał Szczygieł, Michał Pikus, Jarosław Wąs
10:30 Coffee Break / Poster Session  
11:00 Conflict-Component Decomposition for Quantum-Ready Multi-Agent Path Finding Ujjwal Mishra, Dwarikanath Mahapatra, Mohna Chakraborty, Behzad Bozorgtabar, Murari Mandal, Sudipta Roy
11:20 Keynote Hector Geffner
12:30 Lunch Break / Poster Session  
14:00 Neuro-Symbolic Cooperative Multi-Agent Reinforcement Learning Kim Paulke, Jonas Ehrhardt, René Heesch, Oliver Niggemann
14:20 Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning Swapnil Parekh
14:40 SAVGO: Learning State–Action Value Geometry with Cosine Similarity for Continuous Control Stavros Orfanoudakis, Pedro P. Vergara
15:00 Network-Based Interventions for HIV Prevention via Cascade-Aware Suppression of Transmission Akseli Kangaslahti, Davin Choo, Milind Tambe, Alastair van Heerden, Cheryl Johnson
15:20 Closing Remarks  

Submission Details

We solicit workshop paper submissions relevant to the above call of the following types:

We aim to publish the workshop proceedings through CEUR-WS (https: //ceur-ws.org/). This is optional, meaning accepted submissions can choose to be part of the proceedings but don’t have to. Please note that CEUR-WS workshop proceedings are archival. The Latex template can be found here, with more information available here.

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 IJCAI-ECAI main conference to the workshop. You may submit already accepted papers from other conferences if they fit the workshop’s scope. If you submit an already accepted paper, the paper cannot be included in the CEUR-WS workshop proceedings.

As the main purpose of this workshop is to solicit discussion, the authors are invited to use the appendix of their submissions for that purpose.

Paper submissions should be made through OpenReview.

We do not insist on papers being submitted anonymously initially; this decision is left to the discretion of the author. If a paper is simultaneously being considered at a venue where anonymity is required, you have the option to submit it without author details, considering the possibility of a shared reviewer pool.

Organizing Committee

Program Committee

Please send your inquiries to prl.theworkshop@gmail.com

< Link to other workshops in the series