AGENT: A Benchmark for Core Psychological Reasoning

In this seminar, I talk about the recently released paper “AGENT: A Benchmark for Core Psychological Reasoning.

@misc{agent2021shu,
  doi = {10.48550/ARXIV.2102.12321},
  url = {https://arxiv.org/abs/2102.12321},
  author = {Shu, Tianmin and Bhandwaldar, Abhishek and Gan, Chuang and Smith, Kevin A. and Liu, Shari and Gutfreund, Dan and Spelke, Elizabeth and Tenenbaum, Joshua B. and Ullman, Tomer D.},
  keywords = {Artificial Intelligence (cs.AI), Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {AGENT: A Benchmark for Core Psychological Reasoning},
  publisher = {arXiv},
  year = {2021},
  copyright = {arXiv.org perpetual, non-exclusive license}
}