AI 模型发布与服务商更新

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection

Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving

Seir\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning

Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation

OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents

PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement