Sign in

Wenxuan Ding

@wenxuand.bsky.social
26 followers 12 following 8 posts

CS PhD student at NYU wenwen-d.github.io

PostsRepliesMedia
Reposted by Wenxuan Ding
Manya Wadhwa @manyawadhwa.bsky.social · 13/03/2026
⚛️ Introducing CREATE, a benchmark for creative associative reasoning in LLMs. Making novel, meaningful connections is key for scientific & creative works. We objectively measure how well LLMs can do this. 🧵👇
24113
Wenxuan Ding @wenxuand.bsky.social · 23/02/2026
Agents interact with environments to get information. But exploration (tools, retrieval, user interaction) is costly. Calibrate-Then-Act allows LLM agents to balance exploration and cost: 📐 Estimate uncertainty about the environment 💭 Reason about cost-uncertainty tradeoffs ⚙️ Act accordingly
1176