cs.AI（2025-10-28）

📊 共 33 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (2) 支柱四：生成式动作 (Generative Motion) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 Taming the Real-world Complexities in CPT E/M Coding with Large Language Models ProFees：利用大语言模型解决CPT E/M编码的现实复杂性 large language model
2 Discovering Heuristics with Large Language Models (LLMs) for Mixed-Integer Programs: Single-Machine Scheduling 利用大型语言模型发现单机调度启发式算法，显著提升求解效率。 large language model
3 Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading 提出自回归状态追踪提示ASTP，解决LLM在游戏交易中规则遵循问题 large language model
4 Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives 提出数据中心范式，赋能生成式AI在医疗健康领域的应用 large language model foundation model multimodal
5 Human-Level Reasoning: A Comparative Study of Large Language Models on Logical and Abstract Reasoning 对比研究大型语言模型在逻辑与抽象推理能力上的表现，揭示其与人类的差距 large language model
6 Generative Large Language Models (gLLMs) in Content Analysis: A Practical Guide for Communication Research 为提升传播研究内容分析质量，提出基于生成式大语言模型的实践指南 large language model
7 Verifying Large Language Models' Reasoning Paths via Correlation Matrix Rank 提出基于相关矩阵秩的自验证方法，提升大语言模型推理路径的可靠性。 large language model
8 LLMLogAnalyzer: A Clustering-Based Log Analysis Chatbot using Large Language Models LLMLogAnalyzer：一种基于聚类的日志分析聊天机器人，利用大语言模型简化日志分析。 large language model
9 A Unified Geometric Space Bridging AI Models and the Human Brain 提出脑类空间统一框架，跨模态对齐AI模型与人脑认知 large language model multimodal
10 MGA: Memory-Driven GUI Agent for Observation-Centric Interaction MGA：面向观察中心交互的记忆驱动GUI代理，提升GUI任务的鲁棒性和泛化性 large language model multimodal
11 Towards Human-AI Synergy in Requirements Engineering: A Framework and Preliminary Study 提出人机协同需求工程框架HARE-SM，提升需求获取、分析与验证效率。 large language model
12 FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use FunReason-MT：面向真实世界多轮工具使用的高级数据合成方案 large language model
13 The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems 提出叙事连续性测试(NCT)框架，评估AI系统中身份持久性和长期连贯性 large language model
14 From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning 提出基于图的伪标签框架，利用跨任务示例提升上下文学习效率。 large language model
15 Law in Silico: Simulating Legal Society with LLM-Based Agents Law in Silico：提出基于LLM的智能体框架，用于模拟法律社会。 large language model
16 Improving LLM Reasoning via Dependency-Aware Query Decomposition and Logic-Parallel Content Expansion 提出Orion框架以解决LLM推理效率与质量的矛盾问题 large language model
17 VDSAgents: A PCS-Guided Multi-Agent System for Veridical Data Science Automation VDSAgents：基于PCS原则的多智能体系统，用于可信数据科学自动化 large language model
18 Retrieval and Argumentation Enhanced Multi-Agent LLMs for Judgmental Forecasting 提出基于检索与论证增强的多Agent LLM框架，用于提升判断性预测的准确性和可解释性。 large language model
19 MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools MCP-Flow：促进LLM Agent掌握真实、多样且可扩展的MCP工具 large language model ✅
20 Lifecycle-Aware code generation: Leveraging Software Engineering Phases in LLMs 提出生命周期感知的代码生成框架，提升LLM在软件工程任务中的代码正确性。 large language model
21 From Narrative to Action: A Hierarchical LLM-Agent Framework for Human Mobility Generation 提出 Narrative-to-Action 框架，利用分层 LLM 智能体生成更符合人类认知逻辑的出行模式。 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🔗⭐
22 Affordance Representation and Recognition for Autonomous Agents 提出基于模式语言的世界建模方法，提升自主Agent在Web环境的适应性 world model affordance foundation model
23 Scheduling Your LLM Reinforcement Learning with Reasoning Trees 提出基于推理树结构的LLM强化学习调度算法Re-Schedule，提升数学推理准确率。 reinforcement learning large language model
24 LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature LeMat-Synth：利用多模态工具箱从科学文献中提取合成流程数据库。 predictive model large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
25 Advancing site-specific disease and pest management in precision agriculture: From reasoning-driven foundation models to adaptive, feedback-based learning 利用推理驱动的基石模型，推进精准农业中特定地点的病虫害管理。 sim-to-real reinforcement learning imitation learning ✅
26 UniPlanner: A Unified Motion Planning Framework for Autonomous Vehicle Decision-Making Systems via Multi-Dataset Integration UniPlanner：面向自动驾驶决策系统的多数据集融合统一运动规划框架 motion planning

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
27 PULSE: Privileged Knowledge Transfer from Electrodermal Activity to Low-Cost Sensors for Stress Monitoring PULSE：利用EDA的特权知识迁移，提升低成本传感器在压力监测中的性能 PULSE
28 Unsupervised local learning based on voltage-dependent synaptic plasticity for resistive and ferroelectric synapses 提出基于电压依赖突触可塑性的无监督局部学习方法，适用于阻变和铁电突触。 PULSE

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
29 The Evolution of Probabilistic Price Forecasting Techniques: A Review of the Day-Ahead, Intra-Day, and Balancing Markets 综述概率性价格预测技术，解决电力市场不确定性问题，覆盖日前、日内和平衡市场。 penetration
30 Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation MGAudio：提出模型引导的双重角色对齐方法，用于高保真开放域视频到音频生成。 classifier-free guidance ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
31 BLM$_1$: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning 提出BLM$_1$以解决跨空间、跨任务和跨体现学习问题 cross-embodiment vision-language-action VLA

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
32 Design and Optimization of Cloud Native Homomorphic Encryption Workflows for Privacy-Preserving ML Inference 提出云原生同态加密工作流优化方案，解决隐私保护机器学习推理难题。 OMOMO

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
33 AIRMap: AI-Generated Radio Maps for Wireless Digital Twins AIRMap：利用AI生成无线数字孪生所需的无线电地图，实现超快速信道建模。 elevation map

⬅️ 返回 cs.AI 首页 · 🏠 返回主页