Deburring the jagged frontier of AI.
* Applying human judgment where AI lacks context
* Recognizing where AI unexpectedly overperforms
* Translating both into real-world outcomes
Excited to see this paper by you, @hengjinlp and her @UofIllinois students being accepted to #ACL2026 main conference. It was fun to have partnered with you all and looking forward to more.
cc: @eightfoldai@Viven_Twins
Can we trust LLMs to manage our time? ⏰
Our recent work (accepted by #ACL2026 main conf🎉) gives the answer!
Our CalendarConflictBench shows that even strong models make up to 35% errors when resolving calendar conflicts on users’ behalf.🥲But no worries! Meet PEARL: We design a RL recipe to train a self-evolving agent that learn and adapt to user preferences over long-horizon for preference-driven decision-making, reducing errors by 55%🚀
Paper: https://t.co/0MjAp90Qzz
Personalization tips by @nngroup: create & review roles, personalize content & functionality, provide outs & view-as https://t.co/Ov5kizYypj