OP-Mix (On-Policy Mix), a data mixing algorithm that operates across pretraining, midtraining, and instruction tuning, is introduced, suggesting a different view of language model training: not a sequence of distinct phases, but a single continuous process of learning from data.
Michael Y Hu, Apurva Gandhi, Kyunghyun Cho et al.· arXiv.org· 0 citations
Can AI agents carry out research on open scientific problems? We introduce Into the Unknown, a benchmark that provides an agent with a science paper along with a research direction to pursue and tasks it to write a follow-up paper. We work with scientists at US Department of Energy (DOE) national laboratories, who each...
Seungone Kim, Jia-Yi Geng, Young-Jun Lee et al.· 3 citations· ⚡1
This work proposes test-time adaptation through human-agent interaction (TAHI), which integrates these signals into agent context and weights, and crystallizes each user's training and evaluation criteria via an evolving rubric module.
