Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Training-Free Prompt Selection for Efficient Reinforcement Learning With Partial Rollouts
Lei Jiang, Honghui Bao, Yue Zhou +3
Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for training reasoning models, but its computational cost makes efficient data selection i…
cs.AI2026
MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition
Yifan Bao, Xinyu Xi, Xinyu Liu +8
Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, training procedure, evaluation p…