YL

Yuquan Lu

cs.AIcs.LGcs.CVcs.MA

On Valency

published · living versions

W_kbpfrmbk·v1 · currentpublished

What RL Brings to Reasoning: A Few Decisions the Base Model Would Not Make

with Siyu Zhang, Yoshua Y. Li, Yifan Ding, Kun Zeng +5

1 version

Preprints & journals

7 papers in the corpus · 2026

EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning2608.06197v2 · Zishan Xu, Zhiyuan Yao, Yuxin Chen et al.2026 · 0 citationsarXiv

SAF-OPD: Stable Advantage Fusion for On-Policy Distillation2607.29209v1 · Yifan Ding, Xincheng Wei, Yoshua Y. Li et al.2026 · 0 citationsarXiv

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution2607.26784v1 · Zhiyuan Yao, Yuxin Chen, Zhengxi Lu et al.2026 · 0 citationsarXiv

SIGMA: Skill-Incidence Graphs for Compositional Multi-Agent Design2606.19758v1 · Kun Zeng, Yu Huo, Siyu Zhang et al.2026 · 0 citationsarXiv

From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs2606.17648v3 · Siyue Chen, Yifu Guo, Yuquan Lu et al.2026 · 0 citationsarXiv

EDIS: Diagnosing LLM Reasoning via Entropy Dynamics2602.01288v2 · Chenghua Zhu, Siyan Wu, Xiangkang Zeng et al.2026 · 0 citationsarXiv

Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought2601.21081v2 · Yu Huo, Siyu Zhang, Kun Zeng et al.2026 · 0 citationsarXiv

Career total: 8 works. 7 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.