cs.AI（2026-06-11）

📊 共 54 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (35 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱一：机器人控制 (Robot Control) (5 🔗1) 支柱四：生成式动作 (Generative Motion) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (35 篇)

#题目一句话要点标签🔗⭐
1 Aligning Quantum Operators with Large Language Models 提出量子算子与大语言模型对齐的方法以解决量子表示理解问题 large language model foundation model language conditioned
2 Reasoning for Mobile User Experience with Multimodal LLMs: Task, Benchmark, and Approach 提出UXBench以评估多模态大语言模型在用户体验中的推理能力 large language model foundation model multimodal
3 Multi-Modal Agents for Power Distribution Defect Detection: An Evaluation of Foundation Models 提出多模态智能体框架以解决电力分配缺陷检测问题 foundation model multimodal
4 Automated reproducibility assessments in the social and behavioral sciences using large language models 利用大型语言模型自动化社会与行为科学的可重复性评估 large language model
5 Why Sampling Is Not Choosing: Intentionality, Agency, and Moral Responsibility in Large Language Models 探讨大型语言模型的意图性与道德责任问题 large language model
6 ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning 提出ARMOR-MAD以解决多代理辩论中的计算浪费问题 large language model
7 PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization 提出PRISMR以解决多模态列表排名中的解析崩溃问题 multimodal
8 GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models 提出GeoNatureAgent基准以评估环境地理空间分析的LLM代理 foundation model
9 MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs 提出MLUBench以解决多模态大语言模型的终身遗忘问题 large language model multimodal ✅
10 Adaptive Turn-Taking for Real-time Multi-Party Voice Agents 提出ModeratorLM以解决多方语音代理的轮流发言问题 large language model chain-of-thought
11 Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints 提出跨模态分析框架以解决医学影像AI中的幻觉问题 foundation model chain-of-thought
12 TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data? 提出TerraBench以解决异构地球系统数据推理问题 large language model foundation model
13 VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation 提出VHDLSuite以解决VHDL生成评估不足的问题 large language model
14 Zero-source LLM Hallucination Detection with Human-like Criteria Probing 提出人类标准探测机制以解决零源LLM幻觉检测问题 large language model ✅
15 Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formalization 提出半自主形式化方法以解决定理验证中的可重用性问题 large language model
16 A Multi-Agent AI System for Automated High School Transcript Processing: Collaborative Document Analysis at Scale 提出多智能体AI系统以自动化处理高中成绩单问题 multimodal
17 SpheriCity: Designing Trustworthy Conversational AI for Sustainability Decision Support 提出SpheriCity以解决可持续性决策支持中的信任问题 large language model
18 MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis 提出MA-ProofBench以解决数学分析领域定理证明评估不足问题 large language model
19 Agents-K1: Towards Agent-native Knowledge Orchestration 提出Agents-K1以解决科学知识编排不足的问题 multimodal
20 A Three-Layer Framework for AI in Scientific Discovery 提出三层框架以提升科学发现中的AI能力 large language model
21 SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents 提出SEVRA-BENCH以评估自动化代码审查中的社会工程漏洞 large language model
22 AgentRivet: an automated system for producing Rivet routines from journal publications 提出AgentRivet以自动生成Rivet例程解决分析覆盖不足问题 large language model
23 Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities 提出Mod-Guide以解决对少数民族不敏感言论的内容审核问题 large language model
24 MiniMax Sparse Attention 提出MiniMax稀疏注意力以解决超长上下文计算问题 multimodal ✅
25 Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents 提出以利益相关者为中心的基准测试以解决网络代理的安全问题 large language model ✅
26 Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm 提出Brick以解决大规模LLM路由中的查询难度问题 multimodal
27 Under What Conditions Can a Machine Be Called Genuinely Creative? 提出机器创造力的十项要求框架以解决人机协作问题 foundation model
28 Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents 提出功能缓存嫁接以解决代码策略生成的延迟与鲁棒性问题 large language model
29 Democracy in the Era of Artificial Intelligence 探讨人工智能如何提升民主治理与参与 large language model
30 The Illusion of Multi-Agent Advantage 提出多智能体系统评估新方法以解决性能误区问题 chain-of-thought
31 Structured Testbench Generation for LLM-Driven HDL Design and Verification-Oriented Data Curation 提出结构化测试平台生成框架以解决LLM驱动RTL设计验证问题 large language model ✅
32 HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness 提出HarnessBridge以解决长任务中代理与环境交互的效率问题 large language model
33 DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks 提出DailyReport基准以评估搜索代理在日常搜索任务中的表现 large language model ✅
34 Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming 提出UOJ-Bench以评估代码生成、黑客攻击与修复能力 large language model
35 (Human) Attention Is (Still) All You Need: Human oversight makes AI-assisted social science reliable 提出人机协作经济研究框架以提升AI辅助社会科学研究的可靠性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
36 A Tutorial on World Models and Physical AI 提出世界模型框架以解决物理AI中的推理与决策问题 world model world models foundation model
37 IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing 提出IterCAD以解决CAD生成与编辑中的迭代交互问题 reinforcement learning multimodal
38 Topical Phase Transitions in Artificial Intelligence Research: Large-Scale Evidence and an Early-Warning Signature for Emerging Topics 提出主题相变模型以识别人工智能研究中的新兴主题 reinforcement learning world model world models ✅
39 ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning 提出ReSum框架以优化大语言模型的推理与总结能力 reinforcement learning large language model
40 Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch 提出基于延迟反馈的多智能体强化学习以优化三方调度目标权重 reinforcement learning policy learning
41 Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning 提出模式匹配推理机制以解决人类与LLM推理一致性问题 world model world models large language model
42 Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response 提出安全合同图多智能体强化学习框架以提升网络安全响应 reinforcement learning
43 EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery 提出EurekAgent以解决自主科学发现中的环境设计问题 Eureka
44 Mental-R1: Aligning LLM Reasoning for Mental Health Assessment 提出CRPO框架以提升心理健康评估的推理能力 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (5 篇)

#题目一句话要点标签🔗⭐
45 From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification 提出ProFact框架以优化多阶段事实验证流程 trajectory optimization reinforcement learning large language model
46 ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm 提出COM-as-Action以解决专业软件操作中的局限性 manipulation visual grounding
47 Physics-Guided Spatiotemporal Learning for Coastal Wave Peak Period Estimation from Video 提出物理引导的时空学习框架以解决近岸波峰周期估计问题 sim-to-real spatiotemporal
48 ERTS: Adversarial Robustness Testing of Ethical AI via Semantic Perturbation in a Bounded Consequence Space 提出ERTS框架以解决伦理AI的对抗鲁棒性测试问题 manipulation
49 TwinBI: An Agentic Digital Twin for Efficient Augmented Interactions with Business Intelligence Dashboards 提出TwinBI以解决商业智能仪表板交互不一致问题 manipulation ✅

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
50 The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems 提出自主渗透评估框架以解决现有评估方法不足问题 penetration large language model
51 AI Receptivity or AI Adoption Breadth? A Tool-Specific Reanalysis of the Lower-Literacy/Higher-Usage Link 重新分析AI素养与工具使用的关系，揭示非文本工具的广泛采用 penetration

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
52 CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation 提出CloudCons以解决云资源整合中的预测与决策问题 PULSE foundation model

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

#题目一句话要点标签🔗⭐
53 Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization 提出MINIM以解决用户界面状态隐私泄露问题 affordance

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
54 Rethinking RAG in Long Videos: What to Retrieve and How to Use It? 提出V-RAGBench和CARVE以解决长视频检索生成问题 egocentric

⬅️ 返回 cs.AI 首页 · 🏠 返回主页