cs.AI（2025-07-30）

📊 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) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Towards Blind Bitstream-corrupted Video Recovery via a Visual Foundation Model-driven Framework	提出基于视觉基础模型的盲比特流损坏视频恢复框架，无需人工标注。	foundation model
2	Automatically discovering heuristics in a complex SAT solver with large language models	AutoModSAT：利用大语言模型自动发现复杂SAT求解器中的启发式策略	large language model
3	OFCnetLLM: Large Language Model for Network Monitoring and Alertness	OFCnetLLM：利用大语言模型进行网络监控和异常预警	large language model
4	A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models	对基于大型语言模型（LLM）的软件漏洞检测方法进行系统性文献综述	large language model	✅
5	aLLoyM: A large language model for alloy phase diagram prediction	提出aLLoyM：一种用于合金相图预测的大语言模型	large language model
6	SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection	SAEL：利用自适应混合专家模型的大语言模型进行智能合约漏洞检测	large language model
7	League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models	提出League of LLMs以解决大型语言模型评估的可靠性问题	large language model
8	Data Readiness for Scientific AI at Scale	提出数据就绪度框架，加速领导级科学数据集上AI基础模型的训练。	foundation model
9	Empirical Evaluation of Concept Drift in ML-Based Android Malware Detection	评估机器学习Android恶意软件检测中概念漂移的影响	large language model
10	Argumentatively Coherent Judgmental Forecasting	提出论证一致性，提升人类和LLM预测的准确性	large language model
11	Moravec's Paradox: Towards an Auditory Turing Test	提出听觉图灵测试基准，揭示AI在复杂听觉场景理解上的显著缺陷	multimodal
12	On LLM-Assisted Generation of Smart Contracts from Business Processes	利用LLM从业务流程生成智能合约：自动化评估框架与性能分析	large language model
13	GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries	GPT-4.1在自动化实验设计中表现卓越，基于新型Python库实现	large language model
14	Enhancing Manufacturing Knowledge Access with LLMs and Context-aware Prompting	利用LLM和上下文感知提示增强制造业知识图谱的访问能力	large language model
15	Metamorphic Testing of Deep Code Models: A Systematic Literature Review	综述：深度代码模型的变质测试研究现状与未来方向	large language model
16	MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines	MetaAgent：基于有限状态机自动构建多智能体系统	large language model
17	Towards Simulating Social Influence Dynamics with LLM-based Multi-agents	利用LLM多智能体模拟在线论坛中的社会影响动力学	large language model
18	An Explainable Emotion Alignment Framework for LLM-Empowered Agent in Metaverse Service Ecosystem	提出可解释的情感对齐框架，提升LLM驱动的元宇宙Agent服务能力	large language model
19	From Articles to Code: On-Demand Generation of Core Algorithms from Scientific Publications	利用科学出版物，实现核心算法的按需生成，替代人工维护的软件库。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
20	RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment	RePaCA：利用推理大语言模型进行静态自动化补丁正确性评估	reinforcement learning large language model chain-of-thought
21	FairReason: Balancing Reasoning and Social Bias in MLLMs	FairReason：平衡多模态大语言模型中的推理能力与社会偏见	reinforcement learning distillation large language model
22	AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads	AutoIndexer：一种强化学习增强的索引推荐器，用于扩展工作负载	reinforcement learning deep reinforcement learning DRL
23	Repair-R1: Better Test Before Repair	Repair-R1：提出一种先测试后修复的自动化程序修复方法，提升修复成功率。	reinforcement learning large language model	✅
24	Open-Source Agentic Hybrid RAG Framework for Scientific Literature Review	提出Agentic混合RAG框架，用于动态、可信的科学文献综述	DPO direct preference optimization

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
25	Systematic Evaluation of Knowledge Graph Repair with Large Language Models	提出基于大语言模型的知识图谱修复系统评估框架，解决现有评估方法缺乏系统性的问题。	VIO large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
26	Magentic-UI: Towards Human-in-the-loop Agentic Systems	Magentic-UI：面向人机协作Agentic系统的开源Web界面	manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页