17 papers
SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
Haolong Hu, Hanyu Li, Tiancheng He +6
MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Y…
A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
Ada Chen, Yongjiang Wu, Junyuan Zhang +6
Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical…
Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
Meng Chen, Kun Wang, Li Lu +2
Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond…
CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
Yongxuan Wu, Xixun Lin, He Zhang +5
LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchan…
AlphaEval: Evaluating Agents in Production
Pengrui Lu, Bingyu Xu, Wenjun Zhang +24
The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure age…
LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models
Wei Zhang, Lintong Du, Yuanhe Zhang +4
Despite the strong performance of Large Language Models (LLMs) on complex instruction-following tasks, precise control of output length remains a persistent challenge. Existing met…