3 papers
cs.CR2026
Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems
Deema Alnuhait, Gengyu Wang, Muhammad Khalifa +1
As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has examined this risk primarily in…
cs.CL2026
From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
Md Nayem Uddin, Kumar Shubham, Eduardo Blanco +2
Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks p…
cs.CL2024
Practical token pruning for foundation models in few-shot conversational virtual assistant systems
Haode Qi, Cheng Qian, Jian Ni +6
In an enterprise Virtual Assistant (VA) system, intent classification is the crucial component that determines how a user input is handled based on what the user wants. The VA syst…