Get started
Author

Zhiwei Shang

Observed name: Shang, Zhiwei
OpenAlex ID: A5124939879
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
2026 · Dash, Pritam, Ge, Tongyu, et al. · arXiv (Cornell University) · 48
PDF
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation
2026 · Qu, Zikun, Zhang, Min, et al. · arXiv (Cornell University) · 9
PDF
Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction
2026 · Kong, Mingze, Qu, Zikun, et al. · arXiv (Cornell University) · 9
PDF
MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks
2026 · Hong, Zhi, Zhang, Qian, et al. · arXiv (Cornell University) · 8
PDF
MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution
2026 · Shang, Zhiwei, Huo, Yu, et al. · arXiv (Cornell University) · 1
PDF
IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems
2026 · Mao, Jie, Lu, Pingchen, et al. · arXiv (Cornell University)
PDF
AuthGateBench: Benchmarking LLMs as Authorization Gate
2026 · Zhuang, Zhixiong, Jia, Jin, et al. · arXiv (Cornell University)
PDF
CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits
2026 · Sun, Jiahang, Shang, Zhiwei, et al. · arXiv (Cornell University)
PDF
Fusion is the New Mutation: Bandit-Guided Evolution on Workflow Graphs
2026 · Shang, Zhiwei, Sun, Jiahang, et al. · arXiv (Cornell University)
PDF
Works count: 9
Citation count: 75
H-index: 4
I10-index: 1
Year
Topic
Type