标题为英语A Three-Pillar Governance Framework for Safe and Trustworthy AI Agents
arXiv:2610.30445v1 Announce Type: new Abstract: AI agents capable of autonomous decision-making introduce significant challenges related to safety, alignment, accountability, and human oversight. Existing Human-in-the-Loop (HITL) and responsible AI approaches provide important…
AI 摘要：要点
- arXiv:2610.30445v1 Announce Type: new Abstract: AI agents capable of autonomous decision-making introduce significant challenges related to safety, alignment, accountability, and human oversight
- Existing Human-in-the-Loop (HITL) and responsible AI approaches provide important…
A Three-Pillar Governance Framework for Safe and Trustworthy AI Agents
相关文章
中国数学家准备1000道题向人工智能发起挑战
🧠 中国数学家准备1000道题向人工智能发起挑战 61岁南京大学教授孙志伟编纂了一部包含1000个未解数学猜想、超过400页的合集。该学者坚信人工智能无法解决……
利用人机协作发现循环突破Lehmer问题中的高次数障碍
arXiv:2610.30277v1 通告类型: new 摘要: 虽然人工智能在数学推理方面取得了快速进展，但许多开放问题依赖于仅通过大规模计算探索和分析综合才能揭示的结构。一个这样的例子……
Route-and-Generate：用于LLM推理路由的KL正则化路由器改进
arXiv:2610.30351v1 通告类型：new 摘要：大语言模型往往不加区分地应用复杂推理，导致在简单任务上过度思考，在困难任务上思考不足。我们提出Route-and-Generate (Rouge)，一种分层训练框架，使得...
ENSoft Ontology Priors over Latent Concept Posteriors for Weakly Supervised Neuro-Symbolic Learning
arXiv:2610.30391v1 Announce Type: new Abstract: Neuro-symbolic (NeSy) predictors that supervise only the task label suffer from reasoning shortcuts: distinct concept mappings achieve the same maximum likelihood, leaving the recovered concepts unidentifiable and unsafe for…