
What If “Agentic” Is a Property of the Environment, Not the Model?
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
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

A practical post. The GitHub repo LLM4Annotation (Zhen-Tan-dmml/LLM4Annotation) is a curated, updated list of papers and tools at the intersection of LLMs and data annotation. If you work in this space, it’s worth bookmarking. What’s in it: The reason it’s worth following — beyond the obvious “saves you a few
