cs.AI（2025-12-31）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 SynRAG: A Large Language Model Framework for Executable Query Generation in Heterogeneous SIEM System SynRAG：用于异构SIEM系统中可执行查询生成的大语言模型框架 large language model
2 RAIR: A Rule-Aware Benchmark Uniting Challenging Long-Tail and Visual Salience Subset for E-commerce Relevance Assessment 提出RAIR：一个面向电商相关性评估的规则感知、长尾和视觉显著性基准 large language model multimodal
3 GenZ: Foundational models as latent variable generators within traditional statistical models GenZ：融合统计模型与大模型的隐变量生成框架，提升预测精度。 large language model multimodal
4 LeanCat: A Benchmark Suite for Formal Category Theory in Lean (Part I: 1-Categories) 提出LeanCat基准测试集，用于评估LLM在范畴论形式化证明中的能力。 large language model
5 Vulcan: Instance-Optimal Systems Heuristics Through LLM-Driven Search Vulcan：利用LLM驱动搜索，合成实例最优的系统启发式算法 large language model
6 Context-aware LLM-based AI Agents for Human-centered Energy Management Systems in Smart Buildings 提出基于LLM的智能建筑能源管理AI Agent，实现情境感知能源管理 large language model
7 AMAP Agentic Planning Technical Report 提出STAgent，一个用于时空理解的Agentic大语言模型，解决复杂任务如POI发现和行程规划。 large language model
8 Semi-Automated Data Annotation in Multisensor Datasets for Autonomous Vehicle Testing 提出一种半自动标注流水线，加速自动驾驶多传感器数据的标注过程。 multimodal
9 DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information DynaFix：一种执行级动态信息驱动的迭代式自动程序修复方法 large language model
10 Chat-Driven Optimal Management for Virtual Network Services 提出聊天驱动的虚拟网络服务优化管理框架，实现意图驱动的网络重配置。 large language model
11 Group Deliberation Oriented Multi-Agent Conversational Model for Complex Reasoning 提出面向群体审议的多智能体对话模型，解决复杂推理任务难题 large language model
12 Recursive Language Models 提出递归语言模型（RLM），解决LLM在超长上下文推理中的难题 large language model
13 MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use MCPAgentBench：构建真实世界MCP工具使用评估基准，提升LLM Agent工具调用能力 large language model
14 Localized Calibrated Uncertainty in Code Language Models 提出代码语言模型局部校准不确定性方法，辅助LLM代码生成质量控制 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
15 Reinforcement Learning-Augmented LLM Agents for Collaborative Decision Making and Performance Optimization 提出强化学习增强的LLM智能体框架，优化协同决策与性能 reinforcement learning large language model
16 Iterative Deployment Improves Planning Skills in LLMs 迭代部署提升大型语言模型在规划任务中的能力 reinforcement learning large language model
17 Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization Youtu-Agent：通过自动生成和混合策略优化提升Agent生产力 reinforcement learning large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页