cs.AI（2025-12-31）

📊 共 26 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) (22 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Placenta Accreta Spectrum Detection using Multimodal Deep Learning 提出基于多模态深度学习的胎盘植入谱检测方法，提升诊断精度。 multimodal
2 Islamic Chatbots in the Age of Large Language Models 分析LLM驱动的伊斯兰聊天机器人对宗教实践的影响与挑战 large language model
3 Developmental trajectories of decision making and affective dynamics in large language models 通过赌博任务和情感评估，揭示大型语言模型决策和情感发展轨迹 large language model
4 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
5 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
6 GenZ: Foundational models as latent variable generators within traditional statistical models GenZ：利用统计模型中的潜在变量生成器作为基础模型，弥合领域知识与数据集特定模式。 large language model multimodal
7 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
8 Constructing a Neuro-Symbolic Mathematician from First Principles 提出Mathesis神经符号架构，解决大语言模型在复杂推理中缺乏公理框架的问题。 large language model
9 Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Control 提出人机协同框架，利用LLM优化库存控制，降低企业成本。 large language model
10 Mortar: Evolving Mechanics for Automatic Game Design Mortar：一种用于自动游戏设计的演化机制 large language model
11 The Agentic Leash: Extracting Causal Feedback Fuzzy Cognitive Maps with LLMs 提出Agentic Leash框架，利用LLM提取因果反馈模糊认知地图 large language model
12 Vulcan: Instance-Optimal Systems Heuristics Through LLM-Driven Search Vulcan：通过LLM驱动搜索合成实例最优的系统启发式算法 large language model
13 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系统，实现情境感知和自然语言交互 large language model
14 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POI发现和行程规划任务。 large language model
15 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标注 multimodal
16 Enhancing Retrieval-Augmented Generation with Topic-Enriched Embeddings: A Hybrid Approach Integrating Traditional NLP Techniques 提出主题增强嵌入，融合传统NLP技术，提升检索增强生成效果 large language model
17 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
18 Chat-Driven Optimal Management for Virtual Network Services 提出聊天驱动的网络管理框架，实现虚拟网络服务的优化管理 large language model
19 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，用于复杂推理任务 large language model
20 Recursive Language Models 提出递归语言模型（RLM），通过推理时扩展处理超长上下文，显著提升长文本任务性能。 large language model ✅
21 MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use 提出MCPAgentBench，用于评估LLM Agent在真实MCP工具使用中的能力。 large language model
22 Localized Calibrated Uncertainty in Code Language Models 提出局部校准不确定性方法，定位代码语言模型生成中的错误 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
23 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
24 From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning 提出多步骤空间推理方法以解决LLMs在规划中的不足 reinforcement learning large language model
25 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
26 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