cs.AI（2025-12-05）

📊 共 30 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (23 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 Multimodal Oncology Agent for IDH1 Mutation Prediction in Low-Grade Glioma 提出多模态肿瘤Agent，融合病理图像与知识推理，用于低级别胶质瘤IDH1突变预测 foundation model multimodal
2 Future You: Designing and Evaluating Multimodal AI-generated Digital Twins for Strengthening Future Self-Continuity 设计并评估多模态AI数字孪生，以增强未来自我连续性 large language model multimodal
3 TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge 提出TinyMyo，一种轻量级EMG基础模型，用于边缘设备上的灵活肌电信号处理 foundation model
4 PRiSM: An Agentic Multimodal Benchmark for Scientific Reasoning via Python-Grounded Evaluation 提出PRiSM：一个基于Python代码执行评估的多模态科学推理Agent基准。 multimodal
5 Using Large Language Models to Create Personalized Networks From Therapy Sessions 利用大型语言模型从治疗记录中构建个性化网络，辅助治疗方案制定。 large language model
6 Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models 提出Safe2Harm语义同构攻击，高效破解大型语言模型的安全限制 large language model
7 MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models 提出MIND框架，增强多模态大模型在复杂推理场景下的逻辑鲁棒性。 large language model multimodal ✅
8 Simulating Life Paths with Digital Twins: AI-Generated Future Selves Influence Decision-Making and Expand Human Choice 提出AI驱动的数字双胞胎以扩展人类决策选择 large language model multimodal
9 On measuring grounding and generalizing grounding problems 提出一种评估符号 grounding 的多维度框架，用于系统性研究意义 large language model
10 The Missing Layer of AGI: From Pattern Alchemy to Coordination Physics 提出UCCT理论和MACI架构，为LLM增加协调层以实现更强的推理和规划能力 large language model
11 ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment ARCANE框架通过多智能体协作实现可解释、可配置的对齐，解决长时程任务中偏好动态调整问题。 large language model
12 Trusted AI Agents in the Cloud Omega：构建云端可信AI Agent平台，实现端到端隔离与可验证信任 large language model
13 FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction FedSight AI：多智能体系统预测联邦基金利率目标，模拟FOMC决策。 large language model
14 Evolutionary System 2 Reasoning: An Empirical Proof 提出演化推理优化框架，提升大语言模型系统2推理能力 large language model ✅
15 MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement MARINE：多智能体递归上下文增强的理论优化与设计，提升LLM推理性能 large language model
16 Ontology Learning with LLMs: A Benchmark Study on Axiom Identification OntoAxiom基准测试揭示LLM在公理识别中的潜力与局限，为本体工程提供支持。 large language model
17 Knowing Your Uncertainty -- On the application of LLM in social sciences 提出LLM不确定性评估框架，助力其在社会科学中的可靠应用 large language model
18 Adjudicator: Correcting Noisy Labels with a KG-Informed Council of LLM Agents Adjudicator：利用知识图谱增强的大语言模型智能体委员会纠正噪声标签 large language model
19 BEAVER: An Efficient Deterministic LLM Verifier BEAVER：一种高效的确定性LLM验证框架，用于保证模型输出满足约束条件 large language model
20 Auto-SPT: Automating Semantic Preserving Transformations for Code Auto-SPT：自动化代码语义保持变换，提升代码克隆检测模型的鲁棒性。 large language model
21 A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems 提出一种利用LLM生成元数据增强RAG系统的企业知识检索框架 large language model
22 Please Don't Kill My Vibe: Empowering Agents with Data Flow Control 提出数据流控制(DFC)赋能LLM Agent，解决数据滥用和安全风险。 large language model
23 ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications ChipMind：提出知识图谱增强的检索式推理框架，解决长文本电路设计规范理解问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
24 Deep Reinforcement Learning Optimization for Uncertain Nonlinear Systems via Event-Triggered Robust Adaptive Dynamic Programming 提出基于事件触发鲁棒自适应动态规划的深度强化学习优化方法，用于不确定非线性系统控制。 reinforcement learning deep reinforcement learning
25 Reinforcement Learning Integrated Agentic RAG for Software Test Cases Authoring 提出Reinforcement Infused Agentic RAG框架，提升软件测试用例自动生成质量。 reinforcement learning PPO large language model
26 A Fast Anti-Jamming Cognitive Radar Deployment Algorithm Based on Reinforcement Learning 提出基于强化学习的快速抗干扰认知雷达部署算法，提升部署效率 reinforcement learning deep reinforcement learning
27 ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-hoc Teammate Modeling 提出ReCollab以解决临时团队协作中的行为建模问题 world model large language model
28 Lyrics Matter: Exploiting the Power of Learnt Representations for Music Popularity Prediction 提出HitMusicLyricNet，利用LLM歌词嵌入提升音乐流行度预测精度。 MAE multimodal
29 Variational Quantum Rainbow Deep Q-Network for Optimizing Resource Allocation Problem 提出VQR-DQN，利用变分量子电路优化资源分配问题 reinforcement learning deep reinforcement learning DRL ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
30 The Seeds of Scheming: Weakness of Will in the Building Blocks of Agentic Systems 提出弱意志概念以分析智能体系统中的不一致性问题 PULSE large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页