[PlanetKR] AAAI Machine Ethics Workshop First CFP

[Marija Slavkovik]

We have the pleasure of organising the AAAI2026 Workshop on Machine Ethics:
 from formal methods to emergent machine ethics.

This is a one day workshop. The workshop will be organized as a single
track with multiple thematic blocks, including dedicated sessions for
formal methods and emergent machine ethics (EME), culminating in joint
panel discussions that explore synergies and productive tensions between
the two approaches.

It is W37
https://aaai.org/conference/aaai/aaai-26/workshop-program-list/#ws37
to be held on January 2026.

We call for high quality submissions in one of the three formats:

Full: A full paper would follow the same format as the AAAI submissions (
https://aaai.org/conference/aaai/aaai-26/submission-instructions/).

Fast review track: papers that fit the workshop topic that were rejected
from AAAI could be resubmitted together with reviews and a cover letter on
how the issues were addressed.

Short: 4 pages extended abstract (same template as
https://aaai.org/conference/aaai/aaai-26/submission-instructions/) that
puts forward work that invites discussion but is not yet mature for
publication.

The topics of this workshop include but are not limited to the
Logics for morality and ethics
Knowledge representation of ethical theories and ethically salient
information
Computational modeling of morality and ethics
Specification of ethical reasoning and behavior
Verification of ethical reasoning and behavior
Formal modeling of ethical accountability item Formal modeling of agent
responsibility
Normative reasoning, concepts, and systems in relation to moral behavior of
artificial agents
systems
Ethical reinforcement learning agents
Runtime monitoring of ethical issues
Dynamic, and formally justified, ethical repair
Emergent Machine Ethics (EME) - foundational theories and frameworks
Comparative life-form analysis for value-neutral ethics exploration
ndividual attachment differences between humans and digital entities
Ethics emergence dynamics in multi-agent AI systems
Autonomous norm formation, internalization, and stabilization
Emergent cooperation without external enforcement
Self-organizing governance in AI ecosystems
Convergence criteria for collaborative ethical systems
Inter-intelligence evaluation and mutual assessment frameworks
Human-AI co-creative guidance mechanisms
Bidirectional ethical influence in human-AI societies
Value alignment through internal emergence rather than external control
Scalable approaches to internal ethical development
Benchmarks and metrics for emergent ethics

Important Dates:

Deadline for fast track submissions: November 10, 2025 AOE
Deadline for submissions:  November 5, 2025 AOE
Notification of acceptance: November 15, 2025 AOE

Submission Site: https://easychair.org/conferences?conf=aaaimew26

More on the workshop
https://www.aialign.net/ws-machine-ethics

Please share this CFP among interested parties.

On behalf of the organisation,


Workshop chairs:

Louise Dennis
Taichiro Endo
Michael Fisher
Ryutaro Ichise
Raynaldo Limarga
Hiroshi Yamakawa
Rafal Rzepka {contact}
Marija Slavkovik {contact}
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://kr.org/pipermail/planetkr/attachments/20250929/f63cba16/attachment.htm>