3 papers
cs.CL2026
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Zhen Zhang, Changyi Yang, Zijie Xia +11
Tokens are the fundamental units of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite it…
cs.AI2026
CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
Zhen Zhang, Kaiqiang Song, Xun Wang +11
AI agents are increasingly used to solve real-world tasks by reasoning over multi-turn user interactions and invoking external tools. However, applying reinforcement learning to su…
cs.IR2026
ScienceDB AI: An LLM-Driven Agentic Recommender System for Large-Scale Scientific Data Sharing Services
Qingqing Long, Haotian Chen, Chenyang Zhao +6
The rapid growth of AI for Science (AI4S) has underscored the significance of scientific datasets, leading to the establishment of numerous national scientific data centers and sha…