Zora Wang(@ZhiruoW):Agents trained on population-scale data can do a lot of things. But ask a professional to stake their reputation on an AI-generated artifact? “Pretty good” isn’t good enough. We introduce TAHI: a Test-time Adaptive agent framework through Human-agent Interaction. Featuring: 📈 Test-time adaptation via context (memory, skills) and weight training ⚡ Efficient adaptation to individual expertise within tens of tasks ✔️ Creating comprehensive rubrics for “non-verifiable” tasks 🔍 Analysis of shared community guidelines vs. personalized tacit expertise

Zora Wang

@ZhiruoW

PhD student @CarnegieMellon (@LTIatCMU @CMU_SCS) building adaptive AI agents | @Google PhD Fellows | Prev: @stanfordnlp @MSFTResearch | fun 👩🏻‍💻 🐈 💃

参加 August 2021

627 フォロー中 2.8K ファン

Zora Wang@ZhiruoW

2026.09.08 13:37

Agents trained on population-scale data can do a lot of things. But ask a professional to stake their reputation on an AI-generated artifact? “Pretty good” isn’t good enough. We introduce TAHI: a Test-time Adaptive agent framework through Human-agent Interaction. Featuring: 📈 Test-time adaptation via context (memory, skills) and weight training ⚡ Efficient adaptation to individual expertise within tens of tasks ✔️ Creating comprehensive rubrics for “non-verifiable” tasks 🔍 Analysis of shared community guidelines vs. personalized tacit expertise