cs.AI（2025-04-20）

📊 共 16 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) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs SWE-Synth：合成可验证的缺陷修复数据，赋能大语言模型解决真实缺陷 large language model
2 AI with Emotions: Exploring Emotional Expressions in Large Language Models 探索大语言模型的情感表达能力，为情感AI应用奠定基础 large language model
3 HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models HealthGenie：结合知识图谱与大语言模型，提供个性化健康饮食指导 large language model
4 Optimizing SIA Development: A Case Study in User-Centered Design for Estuary, a Multimodal Socially Interactive Agent Framework Estuary框架：面向社交互动Agent的用户中心设计案例研究 multimodal
5 UFO2: The Desktop AgentOS UFO2：用于Windows桌面的多智能体AgentOS，提升桌面自动化任务的鲁棒性和准确性。 large language model multimodal
6 PolicyEvol-Agent: Evolving Policy via Environment Perception and Self-Awareness with Theory of Mind 提出PolicyEvol-Agent，通过环境感知、自我认知和心智理论演化策略，提升多智能体博弈性能。 large language model
7 A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents Safe-BeAl框架：提升LLM具身智能体任务规划安全性并进行基准测试 large language model
8 Risk Assessment Framework for Code LLMs via Leveraging Internal States PtTrust：利用内部状态预训练的代码大语言模型风险评估框架 large language model
9 Towards Optimal Circuit Generation: Multi-Agent Collaboration Meets Collective Intelligence CircuitMind：多智能体协作与集体智慧驱动的优化电路生成框架 large language model ✅
10 ReasoningV: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning Model ReasoningV：自适应混合推理模型，高效生成Verilog代码 large language model ✅
11 Learning from Reasoning Failures via Synthetic Data Generation 提出基于推理失败分析的合成数据生成方法，提升大模型推理能力 multimodal
12 Biased by Design: Leveraging AI Biases to Enhance Critical Thinking of News Readers 利用AI偏见增强新闻读者批判性思维的宣传检测工具设计 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🔗⭐
13 Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey 基于多智能体强化学习的LLM元认知能力研究综述 reinforcement learning RLHF distillation
14 Deep Reinforcement Learning for Investor-Specific Portfolio Optimization: A Volatility-Guided Asset Selection Approach 提出基于波动率引导的深度强化学习投资组合优化方法，实现投资者个性化资产配置 reinforcement learning deep reinforcement learning DRL
15 LLM-Enabled In-Context Learning for Data Collection Scheduling in UAV-assisted Sensor Networks 提出基于LLM的上下文学习数据收集调度系统，用于无人机辅助传感器网络。 reinforcement learning deep reinforcement learning DRL
16 FinSage: A Multi-aspect RAG System for Financial Filings Question Answering FinSage：一种用于金融文档问答的多方面RAG系统，提升合规分析准确性。 DPO direct preference optimization large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页