3 papers
cs.AI2026
REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems
Zixing Chen, Xingyuan Liu, Jie Zhu +6
Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interactions between the agent and i…
cs.CL2026
Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue
Yi Wei, Shuo Jiang, Huaixia Dou +5
Large language models have demonstrated conversational capabilities, yet empathetic competence remains challenging. Empathetic support is inherently multi-turn and path-dependent:…
cs.CV2026
SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception
Yiyang Su, Jie Zhu, Feng Liu +2
While foundation models have significantly advanced human recognition across diverse modalities, they predominantly rely on static, geometric feature extraction. This approach fund…