cs.AI（2025-07-24）

📊 共 15 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9) 支柱二：RL算法与架构 (RL & Architecture) (6)

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

#题目一句话要点标签🔗⭐
1 Multimodal Behavioral Patterns Analysis with Eye-Tracking and LLM-Based Reasoning 提出基于眼动追踪和LLM推理的多模态行为模式分析框架，提升认知模式提取效果。 large language model multimodal
2 Rainbow Noise: Stress-Testing Multimodal Harmful-Meme Detectors on LGBTQ Content 提出针对 LGBTQ 内容的恶意 Meme 检测鲁棒性评测基准与文本去噪适配器 multimodal
3 A Foundation Model for Massive MIMO Precoding with an Adaptive per-User Rate-Power Tradeoff 提出基于Transformer的mMIMO预编码基础模型，自适应用户速率-功率权衡。 foundation model
4 Automated Code Review Using Large Language Models with Symbolic Reasoning 提出结合符号推理的大语言模型代码评审方法，提升自动化代码评审的准确性和效率。 large language model
5 MemoCoder: Automated Function Synthesis using LLM-Supported Agents MemoCoder：利用LLM支持的多智能体实现自动化函数合成，解决迭代调试难题。 large language model
6 Initial Steps in Integrating Large Reasoning and Action Models for Service Composition 探索集成大型推理模型与动作模型，实现自动化服务组合 large language model
7 AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code AccessGuru：利用LLM检测并修正HTML代码中的Web可访问性违规 large language model
8 Efficient Agents: Building Effective Agents While Reducing Cost 提出Efficient Agents框架，在保证性能的同时显著降低LLM驱动Agent的成本。 large language model
9 The AlphaPhysics Term Rewriting System for Marking Algebraic Expressions in Physics Exams 提出AlphaPhysics，利用项重写系统自动批改物理考试中的代数表达式 large language model

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

#题目一句话要点标签🔗⭐
10 HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization 提出HARLF框架，结合轻量级LLM和分层强化学习优化金融投资组合。 reinforcement learning deep reinforcement learning DRL
11 Revisiting LLM Reasoning via Information Bottleneck 提出基于信息瓶颈的LLM推理优化框架，提升数学推理能力 reinforcement learning large language model chain-of-thought
12 SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law 提出SafeLadder框架，使SafeWork-R1在安全性和能力上协同进化，显著提升多模态推理模型的安全性。 reinforcement learning RLHF multimodal
13 DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition DxHF：通过交互式分解提供高质量人类反馈，用于LLM对齐 reinforcement learning RLHF large language model
14 Simulation-Driven Reinforcement Learning in Queuing Network Routing Optimization 提出基于仿真驱动的Dyna-DDPG算法，优化排队网络路由决策。 reinforcement learning predictive model
15 Optimising Call Centre Operations using Reinforcement Learning: Value Iteration versus Proximal Policy Optimisation 利用强化学习优化呼叫中心运营：价值迭代与近端策略优化对比 reinforcement learning PPO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页