20 papers
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…
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…
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…
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-…
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…
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.…