collaborators

20 papers

cs.CR2026

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails

Shuo Shi, Rui Yin, Naen Xu +7

Multimodal guard models have emerged as critical safety components for screening content in vision-language systems. While adversarial research has extensively studied jailbreaking…

cs.CL2026

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

Aofan Yu, Chenyu Zhou, Tianyi Xu +8

Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and e…

cs.CL2026

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents

Jingxing Wang, Chenyu Zhou, Zhihui Fu +4

Additional test-time compute can give LLM agents access to more past experience, yet expanding the context or adding rollouts does not necessarily yield greater agent capability. W…

cs.MA2026

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System

Shuai Pan, Yixiang Liu, Jiaye Gao +7

Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-…

cs.CL2026

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory

Huacan Chai, Yukai Wang, Yingxuan Yang +7

Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use evidence distributed across in…

cs.CL2026

POP: Prefill-Only Pruning for Efficient Large Model Inference

Junhui He, Zhihui Fu, Jun Wang +1

Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities. However, their deployment is hindered by significant computational costs.…