Connectionists: [Call for Papers] IJCAI 2025 Workshop on User-Aligned Assessment of Adaptive AI Systems

[YooJung Choi]

[Apologies for cross-posting]

IJCAI 2025 Workshop on User-Aligned Assessment of Adaptive AI Systems
Montreal, QC, Canada | August 16-18, 2025
Workshop Website <https://aair-lab.github.io/aia2025>

Although there is a growing need for independent assessment and regulation
of AI systems, broad questions remain on the processes and technical
approaches that would be required to conceptualize, express, manage,
assess, and enforce such regulations for adaptive AI systems.

This workshop addresses research gaps in assessing the compliance of
adaptive AI systems (systems capable of planning/learning) in the presence
of post-deployment changes in requirements, in user-specific objectives, in
deployment environments, and in the AI systems themselves.

These research problems go beyond the classical notions of verification and
validation, where operational requirements and system specifications are
available a priori. In contrast, adaptive AI systems such as household
robots are expected to be designed to adapt to day-to-day changes in the
requirements (which can be user-provided), environments, and as a result of
system updates and learning. The workshop will feature invited talks by
researchers from AI and formal methods, as well as talks on contributed
papers.

Topics of interest include:

   -

   Assessment of AI system capabilities.
   -

   Algorithmic paradigms for assessment of safety and/or compliance of AI
   systems with evolving regulations.
   -

   Learning predictive models of agent capabilities.
   -

   Self-assessment and monitoring.
   -

   Differential assessment of AI systems following system updates or
   learning.
   -

   Assessment of black-box AI systems.
   -

   Types of assessment frameworks and ecosystems.
   -

   Specification languages and representations for specifying requirements
   on AI systems.
   -

   Assessment of LLM-based agents.
   -

   Specification and assessment of compliance w.r.t. ethics/ethical
   properties.
   -

   Regulation, management, and enforcement of AI assessment paradigms.


INVITED SPEAKERS (TENTATIVE)

Chuchu Fan <https://chuchu.mit.edu/>, Massachusetts Institute of Technology
David Krueger <https://davidscottkrueger.com/>, Mila and University of
Montreal
Michael L. Littman <https://www.littmania.com>, Brown University
Ruqi Zhang <https://ruqizhang.github.io/>, Purdue University

WORKSHOP FORMAT

The workshop will feature invited talks, a selected set of contributed
talks, and discussions. The workshop will be in-person and is scheduled for
one day. IJCAI 2025 will be an in-person event this year, and the workshop
will follow the same format as the conference.

SUBMISSION INSTRUCTIONS

Submissions can describe either work in progress or mature work that has
already been published at another research venue. We also welcome
“highlights” papers summarizing and highlighting results from multiple
recent papers by the authors. Submissions of papers being reviewed at other
venues (NeurIPS, CoRL, ECAI, KR, etc.) are welcome since AIA 2025 is a
non-archival venue and we will not require a transfer of copyright. If such
papers are currently under blind review, please anonymize the submission.

Submissions should use the IJCAI 2025 style
<https://www.overleaf.com/read/gjqkgkdtvjrd#a99c28>. Papers under review at
other venues can use the style file of that venue, but the camera-ready
versions of accepted papers will be required in the IJCAI 2025 format by
the camera-ready deadline. The papers should adhere to the IJCAI Code of
Conduct for the Authors <https://www.ijcai.org/authors_code_of_conduct>,
the IJCAI Code of Ethics <https://www.ijcai.org/code_of_ethics>, and
the NeurIPS
2025 policy on using LLMs <https://neurips.cc/Conferences/2025/LLM>.


Three types of papers can be submitted:

   -

   New full technical papers with the length of up to 7 pages + references
   -

   New short papers with the length between 2 and 4 pages + references
   -

   Previously published papers in their original format (ICML, ICLR, R:SS,
   etc.). For these submissions, if the match with workshop topics is not
   immediately clear, we recommend editing the introduction to clarify
   relevance.

Papers can be submitted via OpenReview at
https://openreview.net/group?id=ijcai.org/IJCAI/2025/Workshop/AIA.
Additional details are available on the workshop website
<https://aair-lab.github.io/aia2025>.

IMPORTANT DATES

   -

   Paper submission deadline: May 16, 2025 (AoE, 11:59 PM UTC-12)
   -

   Author notification: June 06, 2025
   -

   Workshop date: August 16-18, 2025 (Exact date TBD)


ORGANIZING COMMITTEE

Pulkit Verma <https://pulkitverma.net/>, Massachusetts Institute of
Technology
YooJung Choi <https://yoojungchoi.github.io/>, Arizona State University
Georgios Fainekos <https://www.fainekos.net/>, Toyota Motor North America
R&D

Siddharth Srivastava <http://siddharthsrivastava.net/>, Arizona State
University

Hazem Torfah <https://starlab.systems/torfah.html>, Chalmers University of
Technology
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20250414/b0a582e8/attachment.html>