HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning
The HUman-Grounded AGENT Benchmark is introduced, which rethinks human reasoning simulation along three dimensions: (i) from averaged to individualized reasoning, (ii) from behavioral mimicry to cognitive alignment, and (iii) from vignette-based to open-ended data.
Chance Jiajie Li, Zhenze Mo, Yuhan Tang et al.
· 2 citations