Booth 21-25 | AI Data Management Zone | Tokyo Big Sight
There’s a quiet result from Cheng et al. (Renmin University and Microsoft Research, 2026) that I keep coming back to. They gave large language models access to a minimal sandbox
The dominant model for AI-assisted research has been batch processing: submit a query, wait for the system to work through it, receive a result. The interaction is asynchronous, the feedback loop is slow, and the human is largely passive until the output arrives. A paper from early 2026 presents a
