Skip to content
jajamoa / HugAgentView on GitHub
[EMNLP 2026 Oral] HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning. Can an LLM predict what a specific person believes, and what would change their mind? 54 participants, 3 contested domains, 1,742 items, think-aloud interviews with an LLM interviewer. Data, code, chatbot.
☆12Nov 12, 2026Updated this week

Alternatives and similar repositories for HugAgent

Users that are interested in HugAgent are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?