KZ

Kaide Zeng

cs.CVcs.LGcs.AI

On Valency

published · living versions

W_9z5t3p3a·v1 · currentpublished

CoHARL: Co-Evolving Agent Policies and Executable Harnesses with Reinforcement Learning

with Jianwen Chen, Peng Xia, Siwei Han, Zhen-Yu Zhang +3

1 version

Preprints & journals

4 papers in the corpus · 2025–2026

ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents2605.14133v2 · Yuxiang Lai, Peng Xia, Haonian Ji et al.2026 · 0 citationsarXiv

SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read2602.22426v1 · Yibo Peng, Peng Xia, Ding Zhong et al.2026 · 0 citationsarXiv

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning2602.08234v2 · Peng Xia, Jianwen Chen, Hanyang Wang et al.2026 · 0 citationsarXiv

Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers2506.23918v3 · Zhaochen Su, Peng Xia, Hangyu Guo et al.2025 · 0 citationsarXiv

Career total: 6 works. 4 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.