cs.AI（2026-03-25）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱一：机器人控制 (Robot Control) (2) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model	提出AutoProf，通过持久研究世界模型实现自主AI研究指导	world model world models large language model
2	Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage	提出基于策略引导的威胁狩猎框架，利用LLM和Splunk SOC实现自动化威胁分析。	reinforcement learning deep reinforcement learning DRL
3	From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments	提出RL环境多维分类法，揭示强化学习从像素到数字智能体的演进趋势。	reinforcement learning large language model
4	OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework	提出OneSearch-V2，通过潜在推理增强的自蒸馏生成式搜索框架，提升电商搜索效果。	distillation
5	The DeepXube Software Package for Solving Pathfinding Problems with Learned Heuristic Functions and Search	DeepXube：一个基于学习的启发式函数解决路径规划问题的软件包	reinforcement learning deep reinforcement learning	✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Enhanced Mycelium of Thought (EMoT): A Bio-Inspired Hierarchical Reasoning Architecture with Strategic Dormancy and Mnemonic Encoding	提出增强型思维菌丝（EMoT），一种受生物启发的层级推理架构，具备策略性休眠和记忆编码能力。	large language model chain-of-thought
7	Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias	揭示RAG系统中群体公平性问题：探究暴露度、效用和归因偏差的影响	large language model
8	From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring	提出ES-LLMS架构，通过解耦决策与表达，提升自适应辅导的可解释性和可靠性。	large language model
9	DUPLEX: Agentic Dual-System Planning via LLM-Driven Information Extraction	DUPLEX：利用LLM驱动的信息抽取实现Agentic双系统规划	large language model
10	SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systems	提出SCoOP，通过语义一致的意见池化提升多模态视觉-语言模型系统的不确定性量化。	multimodal

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search	提出TIP方法以解决MCP系统中的隐性攻击问题	manipulation large language model
12	Bridging the Evaluation Gap: Standardized Benchmarks for Multi-Objective Search	提出多目标搜索标准化评测基准，弥合评估差距，促进算法公平比较。	motion planning

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

#	题目	一句话要点	标签	🔗	⭐
13	Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents	针对油气企业文档，评估RAG中不同分块策略对检索增强生成的影响	structure preservation large language model multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页