Pinned Loading

1. AISmithLab/CoBRA AISmithLab/CoBRA Public

   [🏆 CHI26 Best Paper] CoBRA: Reproducible control of LLM agent behavior via classic social science experiments

   Python 98 4

2. Social-Atoms/social-sim-arena Social-Atoms/social-sim-arena Public

   Live benchmark for social simulation: models forecast the next public release before it is published. Locked, hashed, scored in public.

   HTML 28 15

3. CogMir CogMir Public

   Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View (ICLR 2025)

   6

4. HumanStudy-Hub/HumanStudy-Bench HumanStudy-Hub/HumanStudy-Bench Public

   HumanStudy-Bench: Community Edition — Standardized human study replays for AI agent evaluation

   Python 6 3

5. Mjolnir Mjolnir Public

   Mjölnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion (AAAI-25 Main Track)

   Python 8

6. MGIA MGIA Public

   MGIA: Mutual Gradient Inversion Attack in Multi-Modal Federated Learning (AAAI-23 Student Abstract)

   Python 8