Hao Zhu

Real-Time Reasoning Agents in Evolving Environments

How Dark Patterns Manipulate Web Agents

AutoLibra: Agent Metric Induction from Open-Ended Human Feedback

GEM: A Gym for Generalist LLMs

Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning

AI Realtor: Towards Grounded Persuasive Language Generation for Automated Copywriting

The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies

Verlog: An Efficient Synchronized Multi-turn RL Framework for LLM Agents

Sotopia-RL: Reward Design for Social Intelligence

Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Interactive AI Agents

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions

LifelongSotopia: Evaluating Social Intelligence Of Language Agents Over Lifelong Social Interactions