WZ
Wenlin Zhong
cs.CLcs.AIcs.LG
On Valency
published · living versionsW_dbaw8ezb·v1 · currentpublished
MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution
with Dian Jin, Jinluan Yang, Kairong Han, Baohong Li +7
1 version
Preprints & journals
6 papers in the corpus · 2025–2026SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection2610.18807v1 · Wenlin Zhong, Hao Wang, Kun Yuan et al.2026 · 0 citationsarXiv
Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization2607.22334v1 · Hao Wang, Kun Yuan, Wenlin Zhong et al.2026 · 0 citationsarXiv
PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairs2604.17543v1 · Yuting Huang, Yinghao Hu, Qian Xiao et al.2026 · 0 citationsarXiv
SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent2602.11551v1 · Wenlin Zhong, Jinluan Yang, Yiquan Wu et al.2026 · 0 citationsarXiv
P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering2601.20649v1 · Wenlin Zhong, Chengyuan Liu, Yiquan Wu et al.2026 · 0 citationsarXiv
Universal Legal Article Prediction via Tight Collaboration between Supervised Classification Model and LLM2509.22119v1 · Xiao Chi, Wenlin Zhong, Yiquan Wu et al.2025 · 0 citationsarXiv
Career total: 6 works. 6 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.