cs.AI（2025-05-27）

📊 共 47 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (30 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (13 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (30 篇)

#题目一句话要点标签🔗⭐
1 MSEarth: A Multimodal Scientific Dataset and Benchmark for Phenomena Uncovering in Earth Science 提出MSEarth以解决地球科学领域多模态基准缺失问题 large language model multimodal
2 Privacy-Preserving Chest X-ray Report Generation via Multimodal Federated Learning with ViT and GPT-2 提出多模态联邦学习框架以实现隐私保护的胸部X光报告生成 multimodal
3 WDMIR: Wavelet-Driven Multimodal Intent Recognition 提出WDMIR框架以提升多模态意图识别精度 multimodal
4 Large Language Models Miss the Multi-Agent Mark 提出多智能体系统理论以提升大型语言模型的应用效果 large language model
5 Complex System Diagnostics Using a Knowledge Graph-Informed and Large Language Model-Enhanced Framework 提出知识图谱与大语言模型结合的诊断框架以解决复杂系统诊断问题 large language model
6 Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) 探讨系统提示对大型语言模型偏见的影响及其透明性问题 large language model
7 StreamLink: Large-Language-Model Driven Distributed Data Engineering System 提出StreamLink以解决数据工程任务效率低下问题 large language model
8 CoderAgent: Simulating Student Behavior for Personalized Programming Learning with Large Language Models 提出CoderAgent以解决个性化编程学习中的数据不足问题 large language model
9 Comparisons between a Large Language Model-based Real-Time Compound Diagnostic Medical AI Interface and Physicians for Common Internal Medicine Cases using Simulated Patients 提出基于大型语言模型的实时复合诊断医疗AI接口以提升内科诊断效率 large language model
10 MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs 提出MME-Reasoning以解决多模态大语言模型逻辑推理评估不足问题 large language model multimodal
11 Robust Hypothesis Generation: LLM-Automated Language Bias for Inductive Logic Programming 提出基于LLM的自动化语言偏差生成框架以提升假设生成能力 large language model symbolic grounding
12 Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations 提出ChemCoTBench以解决化学推理不足的问题 large language model chain-of-thought
13 Policy Induction: Predicting Startup Success via Explainable Memory-Augmented In-Context Learning 提出基于记忆增强的上下文学习框架以预测初创企业成功 large language model
14 Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking 提出SemRank以解决科学论文检索中的语义匹配问题 large language model
15 Make Planning Research Rigorous Again! 提出将规划领域的严谨性应用于大语言模型的规划研究 large language model
16 The Feasibility of Topic-Based Watermarking on Academic Peer Reviews 提出基于主题的水印技术以解决学术同行评审中的归属问题 large language model
17 The Multilingual Divide and Its Impact on Global AI Safety 提出解决语言差距以增强全球AI安全性 large language model
18 Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space 提出扩展策略空间以解决监狱突破攻击问题 large language model ✅
19 Interpreting Social Bias in LVLMs via Information Flow Analysis and Multi-Round Dialogue Evaluation 通过信息流分析与多轮对话评估揭示LVLM中的社会偏见 multimodal
20 Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems 研究群体行为以提升LLM多智能体系统的协作能力 large language model
21 Agent-Environment Alignment via Automated Interface Generation 提出ALIGN框架以解决智能体与环境不匹配问题 large language model ✅
22 AITEE -- Agentic Tutor for Electrical Engineering 提出AITEE以解决电气工程教育中的个性化学习问题 large language model
23 Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement 提出AlignMind以解决软件开发中需求捕捉不足的问题 foundation model
24 RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving 提出RepoMaster以解决GitHub仓库复杂任务自动探索问题 large language model ✅
25 Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving 提出MATH-VF框架以解决LLM数学问题求解的验证问题 large language model
26 Respond to Change with Constancy: Instruction-tuning with LLM for Non-I.I.D. Network Traffic Classification 提出ETooL以解决非独立同分布网络流量分类问题 large language model
27 An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks 提出SE-Jury以解决软件工程任务中生成软件工件评估问题 large language model
28 Code Researcher: Deep Research Agent for Large Systems Code and Commit History 提出Code Researcher以解决系统代码补丁生成问题 large language model
29 GIFARC: Synthetic Dataset for Leveraging Human-Intuitive Analogies to Elevate AI Reasoning 提出GIFARC以提升AI推理能力，解决ARC挑战 large language model
30 MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning 提出MIRROR框架以优化工具学习中的多智能体反思问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (13 篇)

#题目一句话要点标签🔗⭐
31 Large Language Model-enhanced Reinforcement Learning for Low-Altitude Economy Networking 提出大语言模型增强的强化学习框架以解决低空经济网络问题 reinforcement learning reward design large language model
32 Aligning Proteins and Language: A Foundation Model for Protein Retrieval 提出CLIP风格框架以实现蛋白质检索 contrastive learning foundation model multimodal
33 RLJP: Legal Judgment Prediction via First-Order Logic Rule-enhanced with Large Language Models 提出基于一阶逻辑规则增强的大语言模型法律判决预测方法 contrastive learning large language model
34 Learning optimal treatment strategies for intraoperative hypotension using deep reinforcement learning 提出深度强化学习模型以优化手术中低血压治疗策略 reinforcement learning deep reinforcement learning
35 R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning 提出R1-Code-Interpreter以解决LLMs在代码推理中的挑战 reinforcement learning curriculum learning large language model ✅
36 Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning 提出蒸馏方法以超越零强化学习的灵活推理能力 reinforcement learning distillation large language model
37 Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective 提出基于扩散模型的多智能体世界建模方法以提升样本效率 reinforcement learning policy learning world model ✅
38 LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation 提出LLM引导的强化学习框架以解决训练瓶颈问题 reinforcement learning large language model
39 Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic Assignment 提出基于强化学习的顺序路线推荐以解决系统最优交通分配问题 reinforcement learning deep reinforcement learning
40 Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems 提出自优化微调方法以提升LLM推荐系统性能 curriculum learning distillation large language model
41 Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation 提出AIDSAFE以解决LLMs安全推理中的数据生成问题 DPO chain-of-thought ✅
42 RRO: LLM Agent Optimization Through Rising Reward Trajectories 提出RRO以优化大型语言模型的多步任务执行 reinforcement learning large language model
43 A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing 提出RL-LLM-AB测试框架以优化个性化营销中的A/B测试 reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
44 Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting 提出频率嵌入的3D高斯点云以解决宽带RF建模问题 3D gaussian splatting 3DGS gaussian splatting
45 Assured Autonomy with Neuro-Symbolic Perception 提出神经符号感知框架以提升网络物理系统的自主性安全性 scene understanding foundation model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
46 Text-Queried Audio Source Separation via Hierarchical Modeling 提出HSM-TSS框架以解决文本查询音频源分离问题 manipulation
47 ADA: Automated Moving Target Defense for AI Workloads via Ephemeral Infrastructure-Native Rotation in Kubernetes 提出ADA以增强AI工作负载的安全性 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页