cs.AI（2025-02-26）

📊 共 26 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) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (7) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding	提出TheoremExplainAgent，用于生成基于视频的多模态定理讲解，提升LLM的定理理解能力。	large language model multimodal
2	Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation	利用大语言模型作为代理，建模大脑语义表征，解决自然刺激下的语义信息提取难题。	large language model multimodal
3	Simulation of Language Evolution under Regulated Social Media Platforms: A Synergistic Approach of Large Language Models and Genetic Algorithms	提出基于LLM和遗传算法的框架，模拟社交媒体监管下的语言进化。	large language model
4	OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents	提出OS-Kairos以解决自主GUI代理过度执行问题	large language model multimodal	✅
5	A Temporal Planning Framework for Multi-Agent Systems via LLM-Aided Knowledge Base Management	提出PLANTOR框架，利用LLM辅助知识库管理，实现多智能体系统的时序规划	large language model
6	Agentic Mixture-of-Workflows for Multi-Modal Chemical Search	提出CRAG-MoW，用于多模态化学搜索，提升材料发现效率。	large language model
7	Assessing LLMs for Front-end Software Architecture Knowledge	评估大型语言模型在前端软件架构知识方面的能力，以VIPER架构为例。	large language model
8	Less or More: Towards Glanceable Explanations for LLM Recommendations Using Ultra-Small Devices	针对超小型设备，提出基于结构化和时序自适应的LLM推荐可解释性方法	large language model
9	Complex LLM Planning via Automated Heuristics Discovery	提出AutoHD，通过自动启发式搜索提升LLM在复杂规划任务中的性能	large language model
10	Do LLMs exhibit demographic parity in responses to queries about Human Rights?	评估大型语言模型在人权问题上的回应是否具有人口统计学均等性	large language model
11	Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation	Nexus：轻量级可扩展的多智能体框架，用于复杂任务自动化	large language model
12	DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model	DualSpec：通过双频谱引导扩散模型实现文本到空间音频的生成	large language model
13	Talking like Piping and Instrumentation Diagrams (P&IDs)	提出一种基于图检索增强生成（Graph-RAG）的P&ID自然语言交互方法。	large language model
14	Multi-LLM Collaborative Search for Complex Problem Solving	提出MoSA：利用多LLM协同搜索解决复杂推理问题	large language model
15	Data-Efficient Multi-Agent Spatial Planning with LLMs	利用LLM进行数据高效的多智能体空间规划，解决出租车调度问题	large language model
16	Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal	HANKER：通过知识图谱遍历和冗余消除，为LLM不可学习性生成全面的审计数据集	large language model
17	Deep-Bench: Deep Learning Benchmark Dataset for Code Generation	DeepBench：用于深度学习代码生成的新型基准数据集，覆盖完整DL流程。	large language model
18	TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation	TrajLLM：基于模块化LLM增强Agent的真实人类轨迹模拟框架	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
19	InternVQA: Advancing Compressed Video Quality Assessment with Distilling Large Foundation Model	提出基于InternVideo2蒸馏的轻量级模型，用于提升压缩视频质量评估性能	distillation foundation model multimodal
20	XSS Adversarial Attacks Based on Deep Reinforcement Learning: A Replication and Extension Study	提出基于深度强化学习的XSS对抗攻击方法以提升检测有效性	reinforcement learning deep reinforcement learning
21	Self-rewarding correction for mathematical reasoning	提出自奖励校正框架，提升LLM在数学推理中的自我纠错能力。	reinforcement learning large language model chain-of-thought
22	A Multi-Agent DRL-Based Framework for Optimal Resource Allocation and Twin Migration in the Multi-Tier Vehicular Metaverse	提出基于多智能体DRL的框架，用于多层车辆元宇宙中的资源优化分配和孪生迁移。	reinforcement learning deep reinforcement learning DRL
23	Conversational Planning for Personal Plans	提出基于LLM的对话式规划框架，用于个性化长期计划制定。	reinforcement learning large language model
24	Combining Planning and Reinforcement Learning for Solving Relational Multiagent Domains	结合规划与强化学习，解决关系型多智能体领域问题	reinforcement learning
25	Integrating Biological and Machine Intelligence: Attention Mechanisms in Brain-Computer Interfaces	综述脑机接口中基于注意力机制的脑电信号分析方法，提升BCI应用性能。	representation learning multimodal

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
26	Homomorphic Encryption of Intuitionistic Logic Proofs and Functional Programs: A Categorical Approach Inspired by Composite-Order Bilinear Groups	提出同态加密框架以扩展直觉逻辑证明与函数程序的应用	OMOMO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页