Yuhang Yao(@yuhang_yao):📣 KDD 2026 is next week! Check out our Blue Sky Ideas work on why stronger models and bolted-on guardrails are not enough for trustworthy multi-agent systems. 🤖 Our GPT and Claude demos reveal failures caused by agent composition, semantic misalignment, data re-identification, and operational loops. Trust must be baked in—not bolted on. 🔐 Demo: https://t.co/3T8hMFEA40 Paper: https://t.co/ToblyT6wkV GitHub:

Yuhang Yao

@yuhang_yao

Senior Research Scientist @ZOOM | PhD @CarnegieMellon | Graph Agent Research

Joined December 2021

117 Following 1K Followers

Yuhang Yao@yuhang_yao

2026.08.07 15:52

📣 KDD 2026 is next week! Check out our Blue Sky Ideas work on why stronger models and bolted-on guardrails are not enough for trustworthy multi-agent systems. 🤖 Our GPT and Claude demos reveal failures caused by agent composition, semantic misalignment, data re-identification, and operational loops. Trust must be baked in—not bolted on. 🔐 Demo: Paper: GitHub: