zzhaires blog
  文章分类
经验贴 1 说说 1 网络科研 12 acmer之路 10 AI学习 12 算法模板 1 附录 1 科研内功 4 thu 1 AI科研 3
读论文 : AGENT SECURITY BENCH (ASB) 读论文 : AGENT SECURITY BENCH (ASB)
读论文 : AGENT SECURITY BENCH (ASB): FORMALIZING AND BENCHMARKING ATTACKS ANDDEFENSES IN LLM-BASED AGENTS摘要总结 AGENT SECURIT
2025-10-16 AI科研
读论文 LLM安全
读论文 : AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection 读论文 : AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
读论文 : AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection摘要 这篇论文主要讨论了AGrail框架，这是一个终身智能体的安全检测
2025-10-16 AI科研
读论文 LLM LLM安全 终生学习
读论文 : Test-Time Learning for Large Language Models 读论文 : Test-Time Learning for Large Language Models
读论文 : Test-Time Learning for Large Language Models摘要这篇论文提出了一种针对大语言模型（LLMs）的测试时学习范式，名为 TLM (Test-Time Learning for Large
2025-10-16 AI科研
读论文 LLM distribution shifts