cs.AI（2025-12-24）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱一：机器人控制 (Robot Control) (2) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Beyond Context: Large Language Models Failure to Grasp Users Intent	大型语言模型未能理解用户意图，易被恶意利用绕过安全机制	large language model
2	Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation	提出Agentic XAI框架，结合SHAP与多模态LLM迭代优化解释质量，应用于农业推荐系统。	large language model multimodal
3	RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic	RoboSafe：通过可执行安全逻辑保障具身智能体的安全	multimodal
4	Scaling Laws for Economic Productivity: Experimental Evidence in LLM-Assisted Consulting, Data Analyst, and Management Tasks	量化LLM规模对经济生产力的影响：咨询、数据分析与管理任务的实验证据	large language model
5	Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking	SPELL：通过句子配对探索LLM在恶意代码生成中的安全漏洞	large language model
6	Mesh-Attention: A New Communication-Efficient Distributed Attention with Improved Data Locality	提出Mesh-Attention，通过优化数据局部性提升分布式Attention的通信效率，加速LLM训练。	large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
7	Embodied AI-Enhanced IoMT Edge Computing: UAV Trajectory Optimization and Task Offloading with Mobility Prediction	提出基于具身AI的IoMT边缘计算框架，优化无人机轨迹和任务卸载，最小化任务完成时间。	trajectory optimization reinforcement learning deep reinforcement learning
8	One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents	RepoNavigator：基于强化学习的单工具LLM智能体，用于仓库级代码定位	manipulation reinforcement learning distillation

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

#	题目	一句话要点	标签	🔗	⭐
9	Policy-Conditioned Policies for Multi-Agent Task Solving	提出基于策略条件策略的程序化迭代最佳响应算法，解决多智能体任务中的策略适应性问题。	reinforcement learning deep reinforcement learning large language model
10	The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents	提出概率框架以解决LLM代理的知识不对称问题	reinforcement learning RLHF

⬅️ 返回 cs.AI 首页 · 🏠 返回主页