cs.AI（2026-06-30）

📊 共 36 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) (18 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (14) 支柱七：动作重定向 (Motion Retargeting) (2) 支柱一：机器人控制 (Robot Control) (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) (18 篇)

#题目一句话要点标签🔗⭐
1 MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments 提出MECoBench以解决多模态智能体在具身环境中的协作问题 large language model multimodal ✅
2 Harnessing Textual Refusal Directions for Multimodal Safety 提出MARS以提升多模态大语言模型的安全性 large language model multimodal
3 ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping 提出ShopX以解决意图驱动购物中的项目履行问题 foundation model instruction following
4 A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems 系统化大型语言模型脆弱性，提升安全防护能力 large language model
5 CLOUDADV: Decision-Aligned Instance Sizing with Zero-Shot Foundation Models under Drift 提出CLOUDADV以解决云实例过度配置问题 foundation model
6 Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models 探讨大型语言模型中的人工群体智能以解决集体决策问题 large language model
7 Benchmarking Large Language Models on Floating-Point Error Classification 提出InterFLOPBench基准以评估LLMs在浮点错误分类中的能力 large language model
8 Minimizing Quantized Semantic Age of Information (QSAoI) in Foundation Model-Based Semantic Communications 提出量化语义信息年龄(QSAoI)以优化6G语义通信资源分配 foundation model
9 Spatial Reasoning via Modality Switching Between Language and Symbolic Representation 提出基于信任度与复杂度的模态切换方法以提升空间推理能力 large language model multimodal
10 PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines 提出PolicyGuard以解决政策合规性文档审查问题 large language model
11 Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2 提出基于模态驱动搜索的整体追踪判断方法以解决ARC-AGI-2问题 large language model
12 Adaptive Cluster-First Route-Second Decomposition for Industrial-Scale Vehicle Routing 提出自适应聚类-优先路线-次级分解方法以解决工业规模车辆调度问题 large language model
13 RAISE: LLM-based Automated Heuristic Design with Robust Adversary Instance Search 提出RAISE框架以解决LLM优化启发式设计的鲁棒性问题 large language model
14 ACE: Pluggable Adaptive Context Elasticizer across Agents 提出ACE模块以解决LLM代理任务中的上下文管理问题 large language model
15 ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents 提出ReGRPO以解决工具使用代理的反射指导问题 multimodal ✅
16 Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling 提出Embodied CAD以解决工业CAD建模中的可靠性问题 large language model
17 ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents 提出ClawArena-Team基准以评估语言模型代理的子代理管理能力 multimodal
18 Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics 提出基于通用编码LLM的自动形式化框架以解决数学研究问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (14 篇)

#题目一句话要点标签🔗⭐
19 Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding 提出Delta-JEPA以解决视觉世界模型中动作敏感性不足的问题 world model world models JEPA
20 A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management 提出三阶段深度强化学习模型以解决个性化投资组合管理中的税务问题 reinforcement learning deep reinforcement learning PPO
21 Optimization Algorithms for Joint OFDM Waveform Design and RIS Configuration in 6G Networks: From Convex Relaxation to Foundation Models 提出联合OFDM波形设计与RIS配置优化算法以解决6G网络问题 PPO foundation model
22 Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration 提出预算环境探测机制以校准世界模型 world model world models
23 World-Model Collapse as a Phase Transition 研究长时间语言代理的世界模型崩溃现象及其相变特性 world model world models
24 PGUDA: Pressure-Guided Unsupervised Domain Adaptation with Cross-Modal Knowledge Distillation for sEMG-Based Gesture Recognition 提出PGUDA框架以解决sEMG手势识别中的领域适应问题 representation learning distillation multimodal
25 GR2 Technical Report 提出GR2框架以提升工业推荐系统的重排序性能 reinforcement learning distillation reward design
26 Long-term Traffic Simulation via Structured Autoregressive Modeling 提出RosettaSim以解决长期交通模拟中的多智能体交互问题 world model world models large language model
27 Think in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using Agents 提出LuckyStar 111B以解决多语言工具使用代理的适应性问题 reinforcement learning instruction following
28 Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs 提出Hard-Routed MoR-LoRA以解决多领域适应问题 reinforcement learning large language model
29 Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index 提出相对惊讶指数以解决RLVR中的令牌选择问题 reinforcement learning large language model
30 Xiaomi-GUI-0 Technical Report 提出Xiaomi-GUI-0以解决真实环境下GUI代理的执行稳定性问题 reinforcement learning multimodal
31 Smart charging of large fleets of Electric Vehicles: Independent Multi-Agent Reinforcement Learning approaches 提出独立多智能体强化学习方法优化电动车充电调度 reinforcement learning
32 SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation 提出SwiftAudio以解决文本到音频生成中的高延迟问题 distillation

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#题目一句话要点标签🔗⭐
33 UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling 提出UniSAE以解决语音属性编辑的灵活性不足问题 motion representation
34 Von Mises Based Uncertainty Quantification for Closely Spaced Automotive Radar Targets 提出基于Von Mises的不确定性量化方法以解决汽车雷达目标估计问题 geometric consistency

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
35 Agentic RAG-VLM: Affordance-Aware Retrieval-Augmented Generation with Self-Reflective Planning for Robotic Grasping 提出Agentic RAG-VLM以解决复杂环境下的机器人抓取问题 manipulation affordance affordance-aware

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

#题目一句话要点标签🔗⭐
36 OpenLife: Toward Open-World Artificial Life with Autonomous LLM Agents 提出OpenLife以推动开放世界人工生命研究 open-vocabulary open vocabulary large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页