Zhuofeng Li

DR-DCI achieves a remarkable 73.3% accuracy in agentic search tasks while efficiently scaling from 100K to 10M documents, outperforming traditional methods.

Masking stale observations can boost search agent accuracy, but only under specific conditions—too much masking can backfire dramatically.

A clever two-stage agent using smaller models can produce better, more substantive peer reviews than brute-force application of the largest LLMs.

Image generation models ace photorealistic art but still choke on screenshots and infographics, highlighting a critical gap in real-world applicability.