3 papers
cs.AI2026
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Weixun Wang, XiaoXiao Xu, Wanhe An +86
Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its impo…
cs.CL2025
Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs
Fei Wei, Daoyuan Chen, Ce Wang +5
Large Language Models (LLMs) excel as passive responders, but teaching them to be proactive, goal-oriented partners, a critical capability in high-stakes domains, remains a major c…
cs.HC2025
The Adaptation Paradox: Agency vs. Mimicry in Companion Chatbots
T. James Brandt, Cecilia Xi Wang
Generative AI powers a growing wave of companion chatbots, yet principles for fostering genuine connection remain unsettled. We test two routes: visible user authorship versus cove…