cs.AI（2026-03-06）

📊 共 19 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models 提出DSH以解决大型语言模型安全机制的解耦问题 large language model
2 Lexara: A User-Centered Toolkit for Evaluating Large Language Models for Conversational Visual Analytics Lexara：一个以用户为中心的工具包，用于评估会话式可视化分析的大型语言模型 large language model
3 Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads 提出SAHA框架，通过攻击深度安全注意力头破解大语言模型的安全对齐。 large language model
4 Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows 提出Schema-Gated Agentic AI，解决科学工作流中确定性与灵活性的矛盾。 large language model
5 MoEless: Efficient MoE LLM Serving via Serverless Computing MoEless：通过Serverless计算实现高效MoE LLM服务 large language model
6 ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code ESAA-Security：一种事件溯源、可验证的AI辅助代码安全审计架构 large language model
7 Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions 对比Bandit与LLM架构，探索个性化健康行为干预中的结构化探索与生成灵活性 large language model
8 The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI EpisTwin：一种基于知识图谱的神经符号架构，用于构建个人AI multimodal
9 Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisation 提出基于逐步PDDL仿真的Agentic LLM规划方法，并进行了实证分析 large language model
10 Sensitivity-Aware Retrieval-Augmented Intent Clarification 提出敏感感知检索增强意图澄清方法，用于保护对话搜索系统中的敏感信息。 large language model
11 An Interactive Multi-Agent System for Evaluation of New Product Concepts 提出基于LLM的多智能体系统，用于自动化评估新产品概念，克服传统方法的主观性和高成本。 large language model
12 Domain-Adaptive Model Merging across Disconnected Modes 提出DMM框架，解决异构域模型在数据隔离下的联邦知识融合问题 multimodal
13 XAI for Coding Agent Failures: Transforming Raw Execution Traces into Actionable Insights 提出一种针对代码Agent失败的XAI方法，将原始执行轨迹转化为可操作的洞察 large language model
14 Evaluating LLM Alignment With Human Trust Models 通过对比提示分析LLM内部信任表征，揭示其社会认知能力 large language model
15 Balancing Domestic and Global Perspectives: Evaluating Dual-Calibration and LLM-Generated Nudges for Diverse News Recommendation 提出双校准算法与LLM生成提示以提升新闻推荐多样性 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🔗⭐
16 Boosting deep Reinforcement Learning using pretraining with Logical Options 提出H^2RL：利用逻辑选项预训练增强深度强化学习，提升长时决策能力 reinforcement learning deep reinforcement learning
17 A Reference Architecture of Reinforcement Learning Frameworks 提出强化学习框架的参考架构，用于统一比较、评估和集成不同的框架。 reinforcement learning
18 Artificial Intelligence for Climate Adaptation: Reinforcement Learning for Climate Change-Resilient Transport 提出基于强化学习的气候适应决策框架，用于提升城市交通系统应对洪涝灾害的能力 reinforcement learning
19 StreamVoiceAnon+: Emotion-Preserving Streaming Speaker Anonymization via Frame-Level Acoustic Distillation 提出StreamVoiceAnon+，通过帧级别声学蒸馏实现情感保留的流式语音匿名化 distillation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页