cs.AI（2026-08-27）

📊 共 36 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) (27) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (3) 支柱六：视频提取与匹配 (Video Extraction) (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) (27 篇)

#题目一句话要点标签🔗⭐
1 GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory 提出GraphMemix以解决多模态代理长期记忆组织问题 foundation model multimodal
2 BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models 提出BrailleBench以解决盲人和聋盲用户的盲文理解问题 large language model
3 Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case 提出ColRel方法以解决数据湖中列关系发现问题 large language model
4 Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation 提出Multi2AV-Safety以评估多模态音视频生成的安全性 multimodal
5 From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities 提出过程级基准以评估LLMs的数学智能能力 large language model multimodal
6 SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers 提出SymbolLKG以解决逻辑推理的可验证性问题 large language model chain-of-thought
7 LLMs Can Design Near-Optimal OR Algorithms 利用大型语言模型设计近似最优的运筹学算法 large language model
8 SWE-Prime: Fewer Trajectories, Better Performance 提出SWE-Prime以优化大语言模型的软件问题解决能力 large language model
9 From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench 提出MCR-Bench以解决多轮代码审查的真实场景问题 large language model
10 Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit 提出Persona-Execution Separation以解决LLM代理执行审计问题 large language model
11 Sophistication in GenAI Use: Field Evidence from a Large Firm 研究生成性AI使用的复杂性及其影响因素 large language model
12 Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance 提出能力框架以提升模型评估合规性 chain-of-thought
13 LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestration 提出层次化角色模型以优化电子设计自动化中的LLM应用 large language model
14 Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents 提出LoopHarness以解决自主LLM代理的安全性问题 large language model
15 LAAF: A Layered Accountability Architecture Framework for LLM Applications 提出LAAF框架以解决大语言模型应用中的问责问题 large language model
16 pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning 提出基于检索增强生成的本体学习方法以解决现有挑战 large language model
17 Evaluating human and LLM screening workflows in a conceptually complex scoping review: Recall--workload trade-offs and run-to-run consistency 比较人类与LLM筛选工作流程以优化文献综述中的回忆与工作负载平衡 large language model
18 C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM Reasoning 提出C-Unseen以解决动态时间知识图中的弱信号检测问题 chain-of-thought
19 BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Click 提出BekchiAI以测量和控制大语言模型代理的能力 large language model
20 LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems 提出LiveSim以解决直播生态系统中用户行为模拟不足的问题 large language model
21 Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training 提出边界校准干预转移方法以优化自主LLM后训练 large language model
22 AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling 提出AgentJudgeBench基准以评估LLM在工具调用中的可靠性 chain-of-thought
23 Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance 提出基于账本控制的自我协调机制以提升LLM编码性能 large language model
24 Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety Moderator 提出Nemotron 3.5以解决多模态内容安全审核问题 multimodal
25 LitCurate: A Configuration-Driven AI-Assisted Framework for Scientific Database Construction with an Application to Lower-Mantle Equation-of-State Data 提出LitCurate框架以解决科学数据库构建问题 large language model
26 LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails 提出LongGuard以解决长文本安全防护失效问题 large language model
27 Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents 提出LoopHarness以解决自主LLM代理的安全性问题 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🔗⭐
28 Omni-Interactive Universal Embedder 提出Omni-Interactive Universal Embedder以解决多模态交互问题 representation learning large language model multimodal
29 Decoupling Planning and Control for Instructable Agents 提出Instruct-to-Act以解决指令生成与执行的脱节问题 behavior cloning world model world models
30 GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RL 提出GRAIN以解决图推理中的名称与叙述转变问题 reinforcement learning large language model
31 WM-R1: Training GUI Agents to Reason and leverage World Models with Reinforcement Learning 提出WM-R1框架以解决GUI代理训练中的资源消耗问题 reinforcement learning world model world models ✅

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
32 PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact? 提出PLCBench框架以评估LLM代理对PLC的物理影响 manipulation large language model
33 AI Control Scientist: LLM-driven Agentic System for Automated Control Design 提出AI控制科学家以解决传统控制设计效率低下问题 model predictive control large language model
34 A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systems 提出多模态AI框架以优化智能边境管控系统的排队管理 MPC model predictive control

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

#题目一句话要点标签🔗⭐
35 TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation 提出多代理框架以解决跨文化表情包转化问题 HuMoR multimodal

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

#题目一句话要点标签🔗⭐
36 A Framework for Object-Centric Predictive Monitoring of Collaborative Processes 提出面向对象的预测监控框架以解决协作过程中的监控问题 semantic mapping semantic map

⬅️ 返回 cs.AI 首页 · 🏠 返回主页