cs.AI（2025-07-04）

📊 共 22 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) (21 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning 提出基于大语言模型增强的逆向规划，实现机器心智理论 large language model chain-of-thought
2 A Tactical Behaviour Recognition Framework Based on Causal Multimodal Reasoning: A Study on Covert Audio-Video Analysis Combining GAN Structure Enhancement and Phonetic Accent Modelling 提出TACTIC-GRAPHS，用于高噪声弱结构下战术视频的语义理解和威胁检测。 multimodal
3 Leveraging Large Language Models for Tacit Knowledge Discovery in Organizational Contexts 利用大型语言模型在组织环境中发现隐性知识 large language model
4 Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language Models 提出基于Agent的架构，自动检测并解决LLM问答系统中问题的不完整性和歧义性。 large language model
5 Roadmap for using large language models (LLMs) to accelerate cross-disciplinary research with an example from computational biology 提出利用大型语言模型加速跨学科研究的路线图，以计算生物学为例 large language model
6 Large Language Models for Combinatorial Optimization: A Systematic Review 综述：大型语言模型在组合优化中的应用研究 large language model
7 Chat2SPaT: A Large Language Model Based Tool for Automating Traffic Signal Control Plan Management Chat2SPaT：基于大语言模型的交通信号控制方案自动管理工具 large language model ✅
8 REAL: Benchmarking Abilities of Large Language Models for Housing Transactions and Services REAL：评估大型语言模型在房地产交易和服务中的能力 large language model
9 LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization LLM4Hint：利用大语言模型为离线查询优化推荐提示，提升泛化性 large language model
10 Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy 利用DSPy框架优化Prompt，提升LLM在多场景下的性能表现 large language model
11 Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky DiaFORGE微调框架提升企业工具调用LLM的真实性和安全性 large language model
12 LogicGuard: Improving Embodied LLM agents through Temporal Logic based Critics 提出LogicGuard以解决长时间序列规划中的决策不可靠问题 large language model
13 RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation RELRaE框架：利用LLM进行XML模式的关系抽取、标注、优化与评估，助力实验室数据知识图谱构建。 large language model
14 EvoAgentX: An Automated Framework for Evolving Agentic Workflows EvoAgentX：自动化演进Agent工作流的开源框架，提升多任务性能。 large language model ✅
15 Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN) 针对ORAN，论文提出并benchmark了向量、图和混合检索增强生成(RAG)流水线，提升了事实正确性和上下文相关性。 large language model
16 Behaviour Space Analysis of LLM-driven Meta-heuristic Discovery 利用LLM驱动的元启发式算法发现方法，通过行为空间分析优化算法性能。 large language model
17 ReservoirChat: Interactive Documentation Enhanced with LLM and Knowledge Graph for ReservoirPy ReservoirChat：利用LLM和知识图谱增强ReservoirPy交互式文档 large language model
18 Effects of structure on reasoning in instance-level Self-Discover 提出iSelf-Discover框架，揭示非结构化推理在复杂问题求解中优于结构化推理。 chain-of-thought
19 Memory Mosaics at scale 扩展记忆镶嵌至LLaMA-8B规模，提升新知识存储和上下文学习能力 large language model
20 CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs CodeAgents：一种用于LLM中高效多智能体推理的Token高效框架 large language model
21 Towards Practical GraphRAG: Efficient Knowledge Graph Construction and Hybrid Retrieval at Scale 提出高效GraphRAG框架，通过低成本知识图谱构建和混合检索，提升企业级应用性能。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
22 A Universal Approach to Feature Representation in Dynamic Task Assignment Problems 提出基于图的动态任务分配通用特征表示方法，提升DRL策略学习效果 reinforcement learning deep reinforcement learning DRL

⬅️ 返回 cs.AI 首页 · 🏠 返回主页