Watt Tool-Use Post-Training
At Watt, I led the tool-calling roadmap for a Llama 3.3-70B model. We fine-tuned it for parallel function calls and multi-turn instruction following. The model reached No. 1 on Berkeley’s Function-Calling Leaderboard V3 in December 2024.
The surrounding workflow supported more than 200 tools. On a 1,000-task multi-step evaluation, task completion improved from 70% to 90%.
About Me
I am an AI Research Scientist on the post-training team at Apodex and one of the founding engineers of Apodex Harness and FrontierAgent. I work on reliable agent systems for long-running tasks: multi-agent orchestration, memory and context management, tool use, and verifiable evaluation. Previously, I led AI development at Watt, a Shanda-incubated startup. I also teach postgraduate deep learning at Nanyang Technological University. My earlier research focused on robot perception and visual SLAM.