cs.AI（2025-09-12）

📊 共 14 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning	提出InPhyRe基准，揭示大型多模态模型在归纳物理推理上的不足	multimodal
2	WALL: A Web Application for Automated Quality Assurance using Large Language Models	WALL：利用大型语言模型实现自动化代码质量保证的Web应用	large language model
3	Smart Trial: Evaluating the Use of Large Language Models for Recruiting Clinical Trial Participants via Social Media	利用大型语言模型进行社交媒体临床试验招募：提出TRIALQA数据集并进行基准测试。	large language model
4	Tackling One Health Risks: How Large Language Models are leveraged for Risk Negotiation and Consensus-building	利用大型语言模型进行风险协商和共识构建，应对“同一个健康”风险	large language model
5	DOCUEVAL: An LLM-based AI Engineering Tool for Building Customisable Document Evaluation Workflows	DOCUEVAL：基于LLM的可定制文档评估工作流AI工程工具	large language model foundation model
6	LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems	系统性分析LLM应用中的威胁与防御，为安全部署提供指导	large language model
7	Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems	提出A2P框架，通过因果推理提升多智能体系统故障归因精度	large language model	✅
8	GenAI Voice Mode in Programming Education	探索GenAI语音模式在编程教育中的应用，解决新手程序员可访问性问题	multimodal
9	The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis	揭示LLM中隐含的道德偏见，探索人机共生的未来	large language model
10	Generating Energy-Efficient Code via Large-Language Models -- Where are we now?	评估LLM生成代码的能效：与人类专家代码的对比分析	large language model
11	Securing LLM-Generated Embedded Firmware through AI Agent-Driven Validation and Patching	提出AI Agent驱动的验证与修补方法，保障LLM生成嵌入式固件安全	large language model
12	LLM Bazaar: A Service Design for Supporting Collaborative Learning with an LLM-Powered Multi-Party Collaboration Infrastructure	提出LLM Bazaar以支持多方协作学习	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization	提出SmartCoder-R1，通过安全感知强化学习提升智能合约生成安全性和可解释性。	reinforcement learning large language model chain-of-thought
14	Reinforcement learning for spin torque oscillator tasks	利用强化学习实现自旋扭矩振荡器（STO）的自动同步控制	reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页