Recognising, Anticipating, and Mitigating LLM Pollution of Online Behavioural Research7просмотровгод назад
Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data1просмотргод назад
CoT-Self-Instruct: Building High-Quality Synthetic Prompts for Reasoning and Non-Reasoning Tasks5просмотровгод назад
Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Gene6просмотровгод назад
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition2просмотрагод назад
Conferences for Multi-Agent Systems Applications: Submission Opportunities the end 20254просмотрагод назад
