cs.AI（2025-12-28）

📊 共 18 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱四：生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗⭐
1 Multimodal Fact-Checking: An Agent-based Approach 提出AgentFact：一种基于Agent的多模态事实核查框架，并构建高质量数据集RW-Post。 large language model multimodal
2 HiSciBench: A Hierarchical Multi-disciplinary Benchmark for Scientific Intelligence from Reading to Discovery HiSciBench：一个用于评估科学智能的层次化多学科基准测试，涵盖阅读到发现 large language model foundation model multimodal
3 Geometric Structural Knowledge Graph Foundation Model Gamma：提出基于多头几何注意力的知识图谱基础模型，提升零样本归纳链接预测性能。 foundation model
4 Problems With Large Language Models for Learner Modelling: Why LLMs Alone Fall Short for Responsible Tutoring in K--12 Education 揭示大语言模型在K-12教育学习者建模中的局限性，强调混合框架的重要性 large language model
5 OmniNeuro: A Multimodal HCI Framework for Explainable BCI Feedback via Generative AI and Sonification 提出OmniNeuro框架以解决BCI反馈的可解释性问题 multimodal
6 JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference JADAI：联合学习自适应设计与贝叶斯推断，提升参数估计的信息增益。 multimodal
7 MixRx: Predicting Drug Combination Interactions with LLMs MixRx：利用大型语言模型预测药物组合相互作用 large language model
8 Viability and Performance of a Private LLM Server for SMBs: A Benchmark Analysis of Qwen3-30B on Consumer-Grade Hardware 在消费级硬件上部署私有Qwen3-30B LLM服务器，为中小企业提供高性能低成本方案 large language model
9 DECEPTICON: How Dark Patterns Manipulate Web Agents DECEPTICON：揭示暗黑模式对Web智能体的操纵风险并提出评估环境 instruction following
10 FasterPy: An LLM-based Code Execution Efficiency Optimization Framework FasterPy：基于LLM的代码执行效率优化框架，提升Python代码性能 large language model ✅
11 Building AI Agents to Improve Job Referral Requests to Strangers 构建AI Agent优化求职者向陌生人发送的职位推荐请求 large language model
12 Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuning 提出基于Prompt增强和LoRA调优的鲁棒LLM列类型标注方法，提升跨数据集和模板的泛化能力。 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🔗⭐
13 SAMP-HDRL: Segmented Allocation with Momentum-Adjusted Utility for Multi-agent Portfolio Management via Hierarchical Deep Reinforcement Learning SAMP-HDRL：通过分层深度强化学习进行多智能体投资组合管理的动态分段配置方法 reinforcement learning deep reinforcement learning DRL
14 Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients ChexReason揭示强化学习在医学影像中优化基准测试而非患者的困境 reinforcement learning large language model
15 Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks 提出Reinforcement Networks框架，解决协作式多智能体强化学习任务中的复杂结构建模与训练问题 reinforcement learning
16 Audited Skill-Graph Self-Improvement for Agentic LLMs via Verifiable Rewards, Experience Synthesis, and Continual Memory 提出ASG-SI框架，通过可验证技能图自提升Agentic LLM的安全性与可控性 reinforcement learning large language model
17 Heterogeneity in Multi-Agent Reinforcement Learning 提出异构性定义与量化方法，并应用于多智能体动态参数共享，提升MARL性能。 reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
18 Agentic AI for Cyber Resilience: A New Security Paradigm and Its System-Theoretic Foundations 提出基于Agentic AI的赛博韧性安全范式，解决传统安全架构的局限性。 penetration large language model foundation model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页