| 1 |
OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft |
提出Chain of Action框架，解决Minecraft中通用智能体动作空间选择难题。 |
generalist agent vision-language-action VLA |
✅ |
|
| 2 |
Large Language Models for Security Operations Centers: A Comprehensive Survey |
综述：大型语言模型在安全运营中心的应用 |
large language model |
|
|
| 3 |
Testing for LLM response differences: the case of a composite null consisting of semantically irrelevant query perturbations |
提出一种新的假设检验方法，用于评估LLM对语义无关扰动的鲁棒性。 |
large language model |
|
|
| 4 |
When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning |
研究LLM在嵌入式机器学习代码生成中的失效模式与原因 |
large language model |
|
|
| 5 |
Public Data Assisted Differentially Private In-Context Learning |
提出公共数据辅助的差分隐私上下文学习方法，提升隐私保护下的ICL效用 |
large language model |
|
|
| 6 |
Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding |
提出HaPLa，利用归纳框架和符号编码破解大型语言模型的安全限制。 |
large language model |
|
|
| 7 |
LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering |
提出基于领域专家心智模型的因果提示工程，减少LLM幻觉 |
large language model |
|
|
| 8 |
AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise |
AgentArch：企业级Agent架构综合评测基准，揭示模型特定架构偏好 |
large language model |
|
|