cs.AI（2025-07-20）

📊 共 10 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) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2)

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

#	题目	一句话要点	标签	🔗	⭐
1	AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning	AlphaAlign：通过极简强化学习激励LLM安全对齐，提升安全性和实用性。	reinforcement learning reward design large language model
2	Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies	提出非线性因果归约方法，解释强化学习策略的成败原因	reinforcement learning
3	Feedback-Induced Performance Decline in LLM-Based Decision-Making	研究表明，基于LLM的决策系统在复杂MDP环境中，反馈机制可能导致性能下降。	reinforcement learning large language model
4	AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents	AgentFly：用于LM Agent的可扩展强化学习框架，提升智能体自主完成任务能力。	reinforcement learning
5	From Kicking to Causality: Simulating Infant Agency Detection with a Robust Intrinsic Reward	提出基于因果推理的内在奖励CAIS，解决婴儿能动性模拟中传统强化学习的脆弱性问题。	reinforcement learning predictive model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
6	InsightX Agent: An LMM-based Agentic Framework with Integrated Tools for Reliable X-ray NDT Analysis	InsightX Agent：基于LMM的智能体框架，用于可靠的X射线无损检测分析	multimodal chain-of-thought
7	Survey of GenAI for Automotive Software Development: From Requirements to Executable Code	探索GenAI在汽车软件开发中的应用，涵盖需求、合规与代码生成	large language model
8	Redefining Elderly Care with Agentic AI: Challenges and Opportunities	探索Agentic AI在老年护理中的应用：机遇与挑战	large language model	✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
9	NavVI: A Telerobotic Simulation with Multimodal Feedback for Visually Impaired Navigation in Warehouse Environments	NavVI：面向视障人士仓库环境导航的多模态遥操作仿真平台	teleoperation multimodal
10	Integrating Reason-Based Moral Decision-Making in the Reinforcement Learning Architecture	提出一种基于理由的强化学习道德决策框架，用于构建人工道德代理。	humanoid humanoid robot reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页