cs.AI（2025-06-18）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 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 Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts 提出Sysformer以解决大语言模型安全性问题 large language model
2 TRUST: Transparent, Robust and Ultra-Sparse Trees 提出TRUST以解决回归树模型的准确性与可解释性问题 large language model
3 Intelligent Assistants for the Semiconductor Failure Analysis with LLM-Based Planning Agents 提出基于大语言模型的规划代理以优化半导体故障分析 large language model
4 SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence 提出SwarmAgentic以实现完全自动化的智能体系统生成 large language model ✅
5 The Effect of State Representation on LLM Agent Behavior in Dynamic Routing Games 提出统一框架以优化LLM代理在动态路由游戏中的表现 large language model
6 Optimizing Web-Based AI Query Retrieval with GPT Integration in LangChain A CoT-Enhanced Prompt Engineering Approach 提出基于GPT集成的LangChain优化远程学习查询检索方法 large language model
7 Uncovering Intention through LLM-Driven Code Snippet Description Generation 利用LLM驱动的代码片段描述生成揭示开发者意图 large language model
8 Efficient and Generalizable Environmental Understanding for Visual Navigation 提出因果感知导航以解决传统方法在环境理解中的局限性 embodied AI
9 RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments 提出RAS-Eval以解决LLM代理安全评估问题 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🔗⭐
10 Deep Reinforcement Learning Xiangqi Player with Monte Carlo Tree Search 提出深度强化学习与蒙特卡洛树搜索结合的象棋玩家系统 reinforcement learning deep reinforcement learning DRL
11 Multi-Agent Reinforcement Learning for Autonomous Multi-Satellite Earth Observation: A Realistic Case Study 提出多智能体强化学习以解决自主多卫星地球观测问题 reinforcement learning policy learning PPO
12 SLR: Automated Synthesis for Scalable Logical Reasoning 提出SLR框架以实现可扩展的逻辑推理自动合成 curriculum learning large language model
13 Heterogeneous Temporal Hypergraph Neural Network 提出异构时间超图神经网络以捕捉高阶交互关系 representation learning contrastive learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Context manipulation attacks : Web agents are susceptible to corrupted memory 提出计划注入攻击以解决网络代理的内存安全问题 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页