cs.AI（2025-09-08）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Can AI Make Energy Retrofit Decisions? An Evaluation of Large Language Models	评估大型语言模型在建筑节能改造决策中的应用潜力	large language model
2	REMI: A Novel Causal Schema Memory Architecture for Personalized Lifestyle Recommendation Agents	提出REMI：一种因果模式记忆架构，用于个性化生活方式推荐	large language model multimodal
3	From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs	提出基于指导和精炼的结构化推理框架，提升LLM在复杂任务中的性能。	large language model
4	Benchmarking Information Retrieval Models on Complex Retrieval Tasks	构建复杂检索任务基准，评估并提升现有信息检索模型性能	large language model
5	An Ethically Grounded LLM-Based Approach to Insider Threat Synthesis and Detection	提出一种基于伦理的大语言模型方法，用于内部威胁合成与检测	large language model
6	Measuring and mitigating overreliance is necessary for building human-compatible AI	针对大语言模型过度依赖问题，提出测量与缓解策略，保障人机协同。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
7	Reinforcement Learning Foundations for Deep Research Systems: A Survey	综述：深度研究系统的强化学习基础，关注智能体架构、训练方法与评估基准	reinforcement learning DPO multimodal
8	SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents	提出SFR-DeepResearch，通过强化学习提升单智能体自主推理能力。	reinforcement learning large language model
9	TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning	提出TableMind：一个自主可编程的表格推理Agent，增强工具使用能力。	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	🔗	⭐
10	Musculoskeletal simulation of limb movement biomechanics in Drosophila melanogaster	构建果蝇腿部肌肉骨骼模型，揭示运动控制的生物力学机制	locomotion imitation learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页