Dingming Li

Papers that credit Dingming Li in their source bylines. Matching names may refer to different researchers.

1 results

1. PaperAI & Agents

   A weak action chooser can still teach agents which steps help

   

   After-the-task action scores raised Qwen’s task success in ALFWorld and WebShop, compared with outcome-only training.

   Added to Chiosa Nov 13, 2026