Environment
GUI + CLI + Code
Hi! I'm Longtao Zheng.
I build real-world environments for computer agents.
I'm Longtao Zheng (郑龙韬), a researcher at Bytedance, working on RL for coding agents. My research focuses on training open-ended and long-horizon agents. I earned my PhD from Nanyang Technological University (NTU) Singapore in 2026, advised by Prof. Bo An. Previously, I received my Bachelor's degree in computer science from University of Science and Technology of China (USTC) in 2022.
Research
My research studies the full learning loop of computer agents: real-world GUI + CLI + Code environments, long-horizon context management and self-evolution, and training LLM agents with RL.
observation
action
Harness
Long-horizon autonomy
context
reasoning / action
LLM
RL self-improvement
Blogs
Coming Soon
Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
Stable training algorithm and open-source codebase for multi-agent LLM RL
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
A token-level baseline prevents RL training collapse and reduces token consumption
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
Optimizing Triton kernel generation with multi-turn RL and test-time scaling
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Simple trajectory filtering stabilizes multi-turn RL and emerges diverse reasoning
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
Fine-tuning VLM agents with online RL
Cradle: Empowering Foundation Agents Towards General Computer Control
An agent that can play AAA video games
MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation
A SOTA and open-weight model for audio-driven talking video generation
AgentStudio: A Toolkit for Building General Virtual Agents
A trinity of environments, tools, and benchmarks for general virtual agents
A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist
The first multimodal agent for financial trading
Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
One of the earliest web agents with state abstraction, trajectory prompting, and memory
True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning
Fine-tuning LLM agents with online RL
Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification
A causality-based solution to deal with type confounding in ad hoc teamwork
Multi-Agent Multi-Game Entity Transformer: Towards Generalist Models in MARL
A generalist transformer for Honor of Kings, Starcraft II, and Neural MMO
Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning
Autocurricula for MARL in complex sparse-reward environments like Google Football