cs.AI（2026-04-29）

📊 共 12 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation TimeMM：用于动态多模态推荐的时间算子谱滤波框架 multimodal
2 TDD Governance for Multi-Agent Code Generation via Prompt Engineering 提出一种基于提示工程的多智能体代码生成TDD治理框架，提升LLM辅助软件开发的可靠性。 large language model
3 MappingEvolve: LLM-Driven Code Evolution for Technology Mapping MappingEvolve：利用LLM驱动代码进化，优化技术映射 large language model ✅
4 Preserving Disagreement: Architectural Heterogeneity and Coherence Validation in Multi-Agent Policy Simulation 提出AI Council框架，通过架构异构和一致性验证提升多智能体策略模拟的合理分歧。 large language model
5 DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference DUAL-BLADE：用于边缘LLM推理的双路径NVMe直连KV缓存卸载 large language model
6 Tatemae: Detecting Alignment Faking via Tool Selection in LLMs Tatemae：通过LLM工具选择检测对齐伪装行为 chain-of-thought
7 SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization SecMate：利用三重上下文个性化的多智能体自适应网络安全故障排除系统 large language model
8 LATTICE: Evaluating Decision Support Utility of Crypto Agents LATTICE：提出加密代理决策支持效用的评估基准，填补现有评估方法在用户决策辅助方面的空白。 foundation model
9 Persuadability and LLMs as Legal Decision Tools 评估LLM在法律决策中的可说服性，揭示模型易受辩护质量影响的风险 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
10 AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents AGEL-Comp：一种神经符号框架，用于交互式Agent中的组合泛化 world model world models large language model
11 FutureWorld: A Live Environment for Training Predictive Agents with Real-World Outcome Rewards FutureWorld：一个基于真实世界奖励的预测智能体训练实时环境 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
12 Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control 评估大型语言模型在机器人健康助手控制中的安全性 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页