cs.AI（2026-02-22）

📊 共 11 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (6) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
1 K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model K-Search：通过协同演化的内在世界模型生成LLM Kernel，显著提升GPU Kernel优化效率。 world model large language model
2 MagicAgent: Towards Generalized Agent Planning MagicAgent：面向通用智能体规划的基础模型 reinforcement learning large language model foundation model
3 CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG CRCC：基于对比学习的鲁棒脑电跨被试和跨站点表征学习 representation learning contrastive learning
4 Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces 对比表征空间中时间序列、视觉和语言对齐的极限探索 contrastive learning multimodal
5 Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts 提出基于软混合专家模型的强化学习方法，提升定向控制器综合中的探索鲁棒性。 reinforcement learning
6 Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environment 提出基于CityLearn环境的多KPI基准测试，评估MARL在城市能源控制中的性能 reinforcement learning PPO SAC

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
7 Automated Generation of Microfluidic Netlists using Large Language Models 利用大语言模型自动生成微流控网络列表，简化微流控设备设计。 large language model
8 Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playing 通过通用游戏玩耍评估大语言模型的推理能力 large language model
9 City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification 提出一种层级Agent框架，用于依赖感知的城市地理空间编辑，提升城市规划效率。 multimodal
10 Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents 提出Agentic Problem Frames框架，提升领域Agent的可靠性与可验证性 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
11 Limited Reasoning Space: The cage of long-horizon reasoning in LLMs 提出Halo框架，通过动态规划解决LLM长程推理中的过规划问题 model predictive control large language model chain-of-thought

⬅️ 返回 cs.AI 首页 · 🏠 返回主页