Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Rongsheng Li

Rongsheng Li

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2ML×1Crypto×1

Frequent co-authors

Ran Liu1×
Min Yu1×
Mingqi Liu1×
Jianguo Jiang1×
Gang Li1×
Ning Li1×

Research Timeline

2026
The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck

The paper introduces PACT, a provenance-aware runtime monitor that enhances agent security by tracking the origin and trust of individual tool arguments, solving the granularity mismatch in LLM agent defenses.

Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment

The paper introduces AdvCL, a framework that repurposes adversarial perturbations as a geometric control signal to stabilize continual learning in large language models, significantly reducing forgetting and enhancing robustness.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIRecentJun 1, 2026

Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment

Ran Liu, Min Yu, Mingqi Liu, Jianguo Jiang +6 more

The paper introduces AdvCL, a framework that repurposes adversarial perturbations as a geometric control signal to stabilize continual learning in large language models, significantly reducing forgett…

View →
cs.CRcs.AIRecentMay 11, 2026

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck

Linfeng Fan, Ziwei Li, Yuan Tian, Yichen Wang +2 more

The paper introduces PACT, a provenance-aware runtime monitor that enhances agent security by tracking the origin and trust of individual tool arguments, solving the granularity mismatch in LLM agent…

View →