Author

Zhengbo Jiao

Observed name: Jiao, Zhengbo

Institutions: National University of Singapore, Shanghai University of Finance and Economics, Shanghai Jiao Tong University, Zhejiang University, Ludwig-Maximilians-Universität München

Observed institutions: National University of Singapore, Shanghai University of Finance and Economics, Shanghai Jiao Tong University, Zhejiang University, Ludwig-Maximilians-Universität München

OpenAlex ID: A5138132706

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

2026 · Xiao, Chuan, Jiao, Zhengbo, et al. · arXiv (Cornell University) · 14

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis

2026 · Jiao, Zhengbo, Wang, Shaobo, et al. · arXiv (Cornell University) · 14

SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation

2026 · Jiao, Zhengbo, Cheng, Yiming, et al. · arXiv (Cornell University) · 10

Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning

2026 · Jiao, Zhengbo, Wang, Shaobo, et al. · arXiv (Cornell University) · 8

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction

2026 · Jiao, Zhengbo, Wang, Shaobo, et al. · arXiv (Cornell University) · 2

Policy of Thoughts: Scaling LLM Reasoning via Test-time Policy Evolution

2026 · Zhengbo Jiao, Hongyu Xian, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2

The Trinity: Capability-Driven Recursive Self-Improvement for Multimodal Agents

2026 · Tang, Weidong, Wang, Ruiheng, et al. · arXiv (Cornell University) · 1

Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis

2026 · Zhang, Wenlong, Jiao, Zhengbo, et al. · arXiv (Cornell University) · 1

WorldFoundry: Towards Unified Infrastructure for World Intelligence

2026 · Tian, Juanxi, Hou, Jiadong, et al. · arXiv (Cornell University)

Recursive Environment Scaling for General Long-Horizon Agents

2026 · Jing, Lingxiao, Jiao, Zhengbo, et al. · arXiv (Cornell University)

Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning

2026 · Chen, Junkai, He, Yuhao, et al. · arXiv (Cornell University)

CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning

2026 · Yan, Xin, Jiao, Zhengbo, et al. · arXiv (Cornell University)

Works count: 12

Citation count: 52

H-index: 4

I10-index: 3