I am grateful to the #AAMAS community for this recognition and excited to keep exploring this direction at the intersection of reinforcement learning, formal verification, and world models.
Florent Delgrange
📢 Deadline Extended!
The submission deadline for the Adaptive and Learning Agents (ALA) Workshop at #AAMAS2026 (Paphos, Cyprus 🇨🇾) has been extended!
🗓️ Feb 26, 2026
alaworkshop2026.github.io
paper: t.co/x8dJ2lcYwd
Glad to share that my paper,
“Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments”
has been accepted at AAMAS 2026!
📄 Paper: arxiv.org/abs/2602.23997
This recognition means a lot to me. The paper is my vision for a problem I care deeply about: building AI agents that can learn, adapt, and still remain reliable in uncertain, non-stationary settings.
This 'Blue Sky Idea' paper lays out a research agenda for foundation world models: persistent and compositional world models designed to support verification and adaptation of learning agents in a single, principled loop.
The framework unifies reinforcement learning, formal verification, and reactive synthesis to deliver world models that can be checked and queried, enabling agents to synthesize verifiable programs, learn new policies quickly, and maintain correctness while adapting to novelty.
