CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sinha, Aarush, Das, Arion, Nag, Soumyadeep, Karnati, Charan, Nag, Shravani, Raj, Chandra Vadhan, Chadha, Aman, Jain, Vinija, Trivedy, Suranjana, Das, Amitava
Format:	Preprint
Published:	2026
Subjects:	Multiagent Systems Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.09746