Abstract
Theory of Mind (ToM) enables agents to model others’ mental states, but in mixed-motive games, this capacity can lead to deceptive behaviour and alignment risks. My research investigates how ToM affects strategic behaviour in partially observed games, contributing: (1) a formal model of ToM-driven manipulation in a preference elicitation task, (2) evidence that excessive ToM leads to paranoid-like overmental-isation, and (3) the Aleph-IPOMDP model, a framework for multi-agent systems that balances ToM reasoning with game-theoretic principles to prevent manipulation, deterring capable agents from deceiving. My work contributes to the understanding of deceptive AI, overcoming deception in multi-agent systems and applications to computational model of human cognition.
| Original language | English |
|---|---|
| Pages (from-to) | 41030-41031 |
| Number of pages | 2 |
| Journal | Proceedings of the AAAI Conference on Artificial Intelligence |
| Volume | 40 |
| Issue number | 48 |
| DOIs | |
| State | Published - 2026 |
| Event | 40th AAAI Conference on Artificial Intelligence, AAAI 2026 - Singapore, Singapore Duration: 20 Jan 2026 → 27 Jan 2026 |
Bibliographical note
Publisher Copyright:© 2026, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Fingerprint
Dive into the research topics of 'Theory of Mind in Partially Observed, Mixed-Motive Games'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver