ALA 2026

ALA aims to foster collaboration, highlight recent advances, and provide a representative overview of current research on adaptive and learning agents. It serves as an inclusive forum for discussing both theoretical foundations and practical applications, spanning topics such as learning and adaptation in dynamic or open-ended environments, coordination and communication among multiple agents, incentive and mechanism design, and the emergence of collective behaviour in complex systems.

The workshop places particular emphasis on emerging learning paradigms and on methods that enable agents to operate reliably in large-scale, uncertain, or evolving environments. We encourage work that extends established techniques or introduces new frameworks to address the challenges of real-world adaptive and multi-agent systems. Topics of interest include, but are not limited to:

• Reinforcement learning (single- and multi-agent)
• Representation learning for single- and multi-agent systems
• Adaptation in dynamic environments
• Foundation models for adaptive (multi-)agent systems
• Multi-objective optimisation in single- and multi-agent systems
• Model-based RL and planning with learned world models (single- and multi-agent)
• Batch and offline (multi-agent) reinforcement learning
• Integrating learning with symbolic or game-theoretic reasoning
• Game theoretical analysis of adaptive multi-agent systems
• Neurosymbolic and logical reasoning for (multi-agent) decision-making
• Safety, robustness, and trustworthy (multi-agent) reinforcement learning
• Decentralized, federated, and communication-aware multi-agent learning
• Evolutionary and open-ended learning in multi-agent populations
• Co-evolution of agents in a multi-agent setting
• Cooperative exploration and learning to cooperate and collaborate
• Learning and modelling trust, reputation, and social norms in human–AI and multi-agent systems
• Emergent behaviour in adaptive multi-agent systems
• Multi-agent reinforcement learning and control for cyber-physical systems and robotics
• Self-organizing, swarm, and bio-inspired adaptive multi-agent systems
• Human-in-the-loop learning systems
• Applications of adaptive and learning agents and multi-agent systems to real world complex systems

Important Dates (23:59 AoE)

• Submission Deadline: 4 February 2026 26 February 2026
• Notification of acceptance: 20 March 2026 26 March 2026
• Camera-ready copies: 15 April 2026
• Workshop: 25 - 26 May 2026

Submission Details

Papers can be submitted through OpenReview.

We invite submission of original work, up to 8 pages in length (excluding references) in the ACM proceedings format (i.e., following the AAMAS formatting instructions ). This includes work that has been accepted only as a poster or extended abstract at AAMAS 2026, but not as an oral presentation. Additionally, we welcome submission of preliminary results, i.e. work-in-progress, as well as visionary outlook papers that lay out directions for future research in a specific area, both up to 6 pages in length, although shorter papers are very much welcome, and will not be judged differently. Finally, we also accept recently published journal papers in the form of a 2 page abstract.

Furthermore, for submissions that were rejected or accepted as extended abstracts at AAMAS, authors need to also append the received reviews and a pdfdiff.

All submissions will be peer-reviewed (double-blind). Accepted work will be allocated time for poster and possibly oral presentation during the workshop. In line with AAMAS, the workshop will be in person.

When preparing your submission for ALA 2026, please be sure to remove the AAMAS copyright block, citation information and running headers. Please replace the AAMAS copyright block in the main.tex file from the AAMAS template with the following:

    \setcopyright{none}
    \acmConference[ALA '26]%
    {Proc.\@ of the Adaptive and Learning Agents Workshop (ALA 2026)}%
    {May 25 -- 26, 2026}%
    {Paphos, Cyprus, https://alaworkshop2026.github.io/}%
    {Aydeniz, Delgrange, Mohammedalamen, Yang (eds.)}%
    \copyrightyear{2026}
    \acmYear{2026}
    \acmDOI{}
    \acmPrice{}
    \acmISBN{}
    \settopmatter{printacmref=false}
                            

When submitting your paper, you will have the option to provide supplementary material (e.g., code, data, videos). In the case your submission contains an appendix, we encourage the authors to include it at the end of the main paper, after the references, so that reviewers can access it easily.

Program

All times are presented in Paphos local time (EEST, UTC+3).

Monday May 25

Tuesday May 26

Invited Talks

Stefano Albrecht

Affiliation: Nanyang Technological University Singapore

Website: https://agents-lab.org/stefano-albrecht/

Title: TBA

Abstract: TBA

Bio: Stefano V. Albrecht is Associate Professor in the College of Computing and Data Science at Nanyang Technological University Singapore, where he leads the Autonomous Agents Research Group. His research interests span autonomous agents, multi-agent interaction, reinforcement learning, and game theory, with a focus on sequential decision making under uncertainty. He has previously received fellowships from the Royal Society, the Royal Academy of Engineering, the Alexander von Humboldt Foundation, and the German Academic Scholarship Foundation.

Frans Oliehoek

Affiliation: Delft University of Technology

Website: https://fransoliehoek.net/

Title: Model-based reinforcement learning and abstraction: towards interactive learning and decision making

Abstract: In reinforcement learning (RL), we develop techniques to learn to control complex systems, and over the last decade we have seen impressive successes ranging from beating grand masters in the game of Go to real-world applications like chip design, power grid control, and drug design. However, nearly all applications of RL require access to an accurate and lightweight simulator from which huge numbers of trials can be sampled. In this talk, I will cover some settings where this is not the case, and where therefore we need to engage in some form of model-based RL to learn an appropriate model. Specifically, I will give an overview of a number of different problem settings (MDPs, POMDPs, and multiagent problems) and various corresponding approaches to learning and using models of the environment, ranging from deep learning to Bayesian inference and from planning with MCTS variants to model-free RL, highlighting their strong points as well as limitations. Central to all these approaches is the notion of abstraction: how finely do we represent the world when learning and planning, and what impact might such abstractions actually have on theoretical guarantees of MBRL methods?

Bio: Frans A. Oliehoek is Full Professor of Interactive Learning and Decision Making at Delft University of Technology, where he co-leads the Sequential Decision Making group and directs the ELLIS Delft Unit. He received his PhD in Computer Science and MSc in Artificial Intelligence from the University of Amsterdam, and held postdoctoral positions at MIT and Maastricht University. His research lies at the intersection of machine learning, AI, and game theory, with a focus on decision making under uncertainty and multiagent systems.

Katia Sycara

Affiliation: Carnegie Mellon University

Website: https://www.ri.cmu.edu/ri-faculty/katia-sycara/

Title: Online Adaptation to nonstationary teammates

Abstract: Adaptation is one of the cornerstones of effective collaboration among heterogeneous team members. But adaptation is very challenging when it must be done online for as-yet unseen teammates, especially when those partners may change their strategies dynamically throughout the interaction. This nonstationary behavior is often observed in humans, but also in new agent partners where the dynamics of the environment may dictate strategy changes. Adapting in real time to nonstationary novel partners becomes particularly challenging in tasks with time pressure and complex strategic spaces. In this talk, I will discuss challenges and open problems and present our work on a strategy-conditioned cooperator framework that learns to represent, categorize, and adapt to a broad range of potential partner strategies in real time. Our approach dynamically infers and adjusts the partner strategy estimate during interaction. By seeking to minimize tracking error, our agent smoothly adapts to nonstationary strategies. We evaluate our method in a modified version of the Overcooked domain, a complex collaborative cooking environment that requires effective coordination among players with a diverse potential strategy space. Our results demonstrate that our proposed coordinator agent achieves better performance compared to existing baselines when paired with novel human and agent teammates.

Bio: Katia Sycara is the Edward Fredkin Research Professor of Robotics and Associate Director of Faculty at Carnegie Mellon University's Robotics Institute, with affiliated appointments in computer science, machine learning, human-computer interaction, and language technologies. Her research spans AI and machine learning, multi-agent and multi-robot systems, and human-robot teaming. She is a Fellow of IEEE and AAAI, and the recipient of the ACM/SIGART Agents Research Award and the INFORMS Lifetime Research Award.

Previous Editions

This workshop is a continuation of the long running AAMAS series of workshops on adaptive agents, now in its eighteenth year. Previous editions of this workshop may be found at the following urls:

• ALA-25
• ALA-24
• ALA-23
• ALA-22
• ALA-21
• ALA-20
• ALA-19
• ALA-16
• ALA-15
• ALA-12

Program Committee

Organization

• A. Alp Aydeniz (Oregon State University, US)
• Montaser Mohammedalamen (University of Alberta, CA)
• Xue Yang (University of Galway, IE)
• Florent Delgrange (Vrije Universiteit Brussel, BE)

• Enda Howley (University of Galway, IE)
• Daniel Kudenko (Leibniz University Hannover, DE)
• Patrick Mannion (University of Galway, IE)
• Ann Nowé (Vrije Universiteit Brussel, BE)
• Sandip Sen (University of Tulsa, US)
• Peter Stone (University of Texas at Austin, US)
• Matthew Taylor (University of Alberta, CA)
• Kagan Tumer (Oregon State University, US)
• Karl Tuyls (University of Liverpool, UK)

Contact

If you have any questions about the ALA workshop, please contact the organizers at:
ala.workshop.aamas AT gmail.com

For more general news, discussion, collaboration and networking opportunities with others interested in Adaptive Learning Agents then please join our Linkedin Group

• © Adaptive Learning Agents Workshop 2026. All rights reserved.
• Design: HTML5 UP
• Icons made by Freepik from www.flaticon.com are licensed by CC 3.0 BY