ZJ
Zhengbo Jiao
cs.AIcs.CVcs.LGcs.SE
On Valency
published · living versionsW_5mfbyv64·v1 · currentpublished
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
with Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang +15
1 version
Preprints & journals
9 papers in the corpus · 2026Recursive Environment Scaling for General Long-Horizon Agents2610.16397v2 · Lingxiao Jing, Zhengbo Jiao, Yichen Xiang et al.2026 · 0 citationsarXiv
Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning2610.10358v2 · Junkai Chen, Yuhao He, Qianshan Wei et al.2026 · 0 citationsarXiv
Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis2610.03548v1 · Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang et al.2026 · 0 citationsarXiv
CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning2609.32750v1 · Xin Yan, Zhengbo Jiao, Jiaqi Liu et al.2026 · 0 citationsarXiv
SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation2607.05943v1 · Zhengbo Jiao, Yiming Cheng, Yilei Jiang et al.2026 · 0 citationsarXiv
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills2606.07412v1 · Chuan Xiao, Zhengbo Jiao, Shaobo Wang et al.2026 · 0 citationsarXiv
Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis2602.03279v1 · Zhengbo Jiao, Shaobo Wang, Zifan Zhang et al.2026 · 0 citationsarXiv
Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction2602.03414v1 · Zhengbo Jiao, Shaobo Wang, Zifan Zhang et al.2026 · 0 citationsarXiv
Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution2601.20379v2 · Zhengbo Jiao, Hongyu Xian, Qinglong Wang et al.2026 · 0 citationsarXiv
Career total: 9 works. 9 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.