Agent4Edu: Generating Learner Response Data by LLM-based Agents for Intelligent Education Systems (AAAI 2025, Oral Presentation)

Official Code for SIGIR 2022 "A Multi-task Based Neural Model to Simulate Users in Goal Oriented Dialogue Systems". User Simulator generates user-side utterance, predicts user's next action and satisfaction level.

"Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems" in SIGIR'21

In-Context Learning User Simulators for Task-Oriented Dialog Systems

[KDD 2026] An automatic, extensible Framework to Evaluate User-Proxy Agents for Human-Likeness. 🌟 Star if you like it!

A swarm of AI users that test your website in real browsers — visualized as a pixel-art aquarium. Live friction maps, multi-user scenes, up to 1,000 sessions on one laptop.

Modeling user satisfaction dynamics using a discrete Hawkes process

Plug-and-play reproducible web analysis.

An LLM-powered conversational simulation framework for Discord, featuring autonomous action planning, safety filtering, and multi-provider LLM integration for research and controlled testing.

🔬 Educational web automation tool showcasing advanced techniques. 🚫 Not for malicious use. 🎓 Learn responsibly!

Code for paper "IvCDS: An End-to-end Driver Simulator For Personal In-vehicle Conversational Assistant"

Knowledge-state-aware user simulator for evaluating information calibration in LLM assistants (arXiv:2608.17150)

Emulate user activity randomly opening apps through Explorer to generate "legit noise" for EDR and any other log-type collection technology.

Access and test terminal session like a table of chars.

Toolkit and benchmark suite for evaluating user simulators in IR: behavioral realism vs. tester reliability, over one canonical session schema — SIGIR 2026

OpenCode plugin that predicts your next message and shows it as ghost text — role-plays as you using your conversation history. /pred-on to enable.

LLM-based User Simulation Agent for the AgentSociety Challenge. Features Chain-of-Thought reasoning, Iterative RAG, and User Persona extraction. Achieved +5.06% review generation quality over baseline.

Multi-agent beta testing framework where LLaVA vision agents form committees to test web apps. Agents analyze screenshots, discuss actions, vote on consensus, and catch bugs + security vulnerabilities. Playwright browser automation, Streamlit dashboard, FastAPI backend.