Neural Reasoning about Agents’ Goals, Preferences, and Actions


  • Matteo Bortoletto University of Stuttgart
  • Lei Shi University of Stuttgart
  • Andreas Bulling University of Stuttgart



CMS: Conceptual Inference and Reasoning, CMS: Other Foundations of Cognitive Modeling & Systems, CMS: Simulating Human Behavior, KRR: Common-Sense Reasoning


We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks - with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.



How to Cite

Bortoletto, M., Shi, L., & Bulling, A. (2024). Neural Reasoning about Agents’ Goals, Preferences, and Actions. Proceedings of the AAAI Conference on Artificial Intelligence, 38(1), 456-464.



AAAI Technical Track on Cognitive Modeling & Cognitive Systems