cs.AI（2025-08-28）

📊 共 25 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (9) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Embodied AI: Emerging Risks and Opportunities for Policy Action 分析具身智能风险与机遇，为政策制定提供建议 embodied AI
2 OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models OnGoal：利用大语言模型追踪和可视化多轮对话中的会话目标 large language model
3 Meta-learning ecological priors from large language models explains human learning and decision making 提出ERMI模型，利用大语言模型和元学习模拟人类在真实环境中的学习与决策。 large language model
4 Model-Driven Quantum Code Generation Using Large Language Models and Retrieval-Augmented Generation 利用大语言模型和RAG生成模型驱动的量子代码，降低开发成本。 large language model
5 TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning TCIA：面向任务的指令增强方法，提升指令微调LLM在特定场景下的性能。 large language model instruction following
6 AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving AdaptCache：面向低延迟和高质量语言模型服务的KV缓存原生存储分层方案 large language model
7 Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding 通过认知支架增强LLM指令：模糊、符号化和情境化方法 large language model
8 TinyServe: Query-Aware Cache Selection for Efficient LLM Serving TinyServe：面向高效LLM服务的查询感知缓存选择 large language model
9 Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems 提出自适应多维监控算法AMDM，用于Agentic AI系统的实时异常检测与评估。 large language model ✅
10 Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol 针对LLM应用测试，提出分层架构分析与轻量级交互协议AICL large language model
11 Re4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision Re4：基于重写、解析、审查和修订的科学计算Agent large language model
12 Enhancing Health Fact-Checking with LLM-Generated Synthetic Data 提出基于LLM生成合成数据的健康事实核查增强方法 large language model
13 Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM 提出熵面积分数(EAS)，用于量化推理LLM生成过程中的不确定性。 large language model
14 Boosting Skeleton-Driven SMT Solver Fuzzing by Leveraging LLM to Produce Formula Generators Chimera：利用LLM生成公式生成器，提升骨架驱动的SMT求解器模糊测试 large language model
15 AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving 提出AdaptCache以解决LLM服务中的KV缓存延迟问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
16 Large Language Model Integration with Reinforcement Learning to Augment Decision-Making in Autonomous Cyber Operations 融合大型语言模型的强化学习提升自主网络攻防决策能力 reinforcement learning large language model
17 Single Agent Robust Deep Reinforcement Learning for Bus Fleet Control 提出基于单智能体强化学习的公交车队控制方法，解决复杂场景下的公交车拥堵问题。 reinforcement learning deep reinforcement learning SAC
18 Learning to Generate Unit Test via Adversarial Reinforcement Learning 提出UTRL框架，通过对抗强化学习提升LLM生成高质量单元测试的能力。 reinforcement learning large language model
19 AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning AI-SearchPlanner：通过帕累托最优多目标强化学习实现模块化Agent搜索 reinforcement learning large language model
20 Flowing Straighter with Conditional Flow Matching for Accurate Speech Enhancement 提出基于条件流匹配的语音增强方法，优化概率路径提升性能 flow matching
21 Reinforcement Learning for Optimizing Large Qubit Array based Quantum Sensor Circuits 提出基于强化学习与张量网络的量子传感器电路优化方法，提升量子比特阵列性能。 reinforcement learning
22 Human-AI Collaborative Bot Detection in MMORPGs 提出基于对比学习和LLM协同的MMORPG游戏机器人检测框架 representation learning large language model
23 Full-Frequency Temporal Patching and Structured Masking for Enhanced Audio Classification 提出全频带时域分块与结构化掩码，提升音频分类性能与效率。 Mamba SSM
24 AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning 提出AI-SearchPlanner以优化搜索规划与问答任务 reinforcement learning large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
25 Multi-Agent Penetration Testing AI for the Web 提出MAPTA：一种基于多智能体和LLM的Web应用渗透测试AI系统 penetration large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页