1 citations · 1 across the 4 of their papers we have counts for
5 papers
MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
Lingqi Jiang, Jialuo Chen, Jianan Ma +8
Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that agents retrieve and inspect durin…
From Approval to Execution: Reconstruction-Aware Repair Analysis for LLM-Agent Software
Junchi Zhu, Zhenguang Liu, Shaojing Fan +2
Approval mechanisms have become a primary safeguard for consequential actions in LLM-agent software. Yet the action shown for approval is often not the object ultimately consumed:…
Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls
Guoyao Yu, Xiaoqing Sun, Ziqi Huang +13
Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool and orchestrating the order…
Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios
Lixun Ma, Ruolong Ma, Bei Wang +4
Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored. Existing benchmarks often re…
Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval
Zhe Ma, Jianfeng Dong, Shouling Ji +7
Visual retrieval aims to search for the most relevant visual items, e.g., images and videos, from a candidate gallery with a given query item. Accuracy and efficiency are two compe…