Author

Songlin Hu

Observed name: Hu, Songlin

Institutions: Chinese Academy of Sciences, Institute of Information Engineering, University of Chinese Academy of Sciences

Observed institutions: Chinese Academy of Sciences, Institute of Information Engineering, University of Chinese Academy of Sciences

OpenAlex ID: A5124295658

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills

2026 · Lv, Lijia, Tang, Xuehai, et al. · arXiv (Cornell University) · 8

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents

2026 · Xiao, Wenjie, Tang, Xuehai, et al. · arXiv (Cornell University) · 7

MGDIL: Multi-Granularity Summarization and Domain-Invariant Learning for Cross-Domain Social Bot Detection

2026 · Qiao, Boyu, Chen, Yunman, et al. · arXiv (Cornell University) · 1

Diagnosing Retrieval Bias Under Multiple In-Context Knowledge Updates in Large Language Models

2026 · Qiao, Boyu, Guo, Sean, et al. · arXiv (Cornell University) · 1

CogRec: Structure-Cognitive Fast-and-Slow Reasoning for Generative Recommendation

2026 · Liu, Xiang, Su, Jingsong, et al. · arXiv (Cornell University)

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents

2026 · Association for Computational Linguistics 2026, Hu, Songlin, et al. · Underline Science Inc.

FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing

2026 · Wang, Peng, Zhou, Biyu, et al. · arXiv (Cornell University)

RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systems

2026 · Wang, Hui, Hu, Tianzhu, et al. · arXiv (Cornell University)

Works count: 8

Citation count: 17

H-index: 2

I10-index: