Author

Bing Ji

h-index 7 View on Semantic Scholar

We have 2 of 42 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Jailbreak Context Lingers: Divergent Safety Routing and Its Cross-Task Predictability in Tool Agents

It is found that identical safety feedback induces sharply model-dependent behavioral routing rather than uniform protection, establishing a mechanistic lens and a predictive baseline for anticipating the safety and utility trade-offs of post-jailbreak feedback in autonomous agents.

Xi Wang, Song-Lei Jian, Yi-Ming Zhang et al. · 0 citations

SkillSight: Seeing Through Shared Descriptions for Accurate Skill Retrieval

SkillSight, a training-free retrieval framework that calibrates shared background in both semantic and lexical spaces and achieves the best overall performance across three agent models and outperforms LLM Selection by up to 4.97 percentage points.

Jin-Ying Xiao, Bing Ji, Shasha Li et al. · 0 citations