PinnedBill Yuchen Lin, PhDinAi2 BlogSwiftSage: Building AI Agents for Complex Interactive Tasks via Fast and Slow Thinking with LLMsSwiftSage, a novel AI agent inspired by fast-and-slow thinking, designed to optimize LLMs for planning for complex interactive tasks.Jun 21, 2023Jun 21, 2023
Bill Yuchen Lin, PhDinAi2 BlogLLM-Blender: A Simple Ensemble Learning Framework for LLMsOur ACL23 paper introduces a simple yet effective method that can significantly improve LLMs via ensemble learning with ranking and fusing.Jul 19, 2023Jul 19, 2023