Tianyi Men

@tianyi-men · 2 works

Researches task planning for multimodal web agents and GUI automation.

Recent posts by Tianyi Men

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher… - Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opaque Internet data,… · Paper · arxiv.org
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning - Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks into executable actions. While small open source… · Paper · arxiv.org