cs.AI（2026-03-04）

📊 共 16 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Phi-4-reasoning-vision-15B Technical Report	提出Phi-4-reasoning-vision-15B，一种紧凑型开源多模态推理模型，擅长视觉语言任务及科学数学推理。	multimodal chain-of-thought
2	FeedAIde: Guiding App Users to Submit Rich Feedback Reports by Asking Context-Aware Follow-Up Questions	提出FeedAIde以解决用户反馈报告不完整问题	large language model multimodal
3	RAGNav: A Retrieval-Augmented Topological Reasoning Framework for Multi-Goal Visual-Language Navigation	RAGNav：一种检索增强的拓扑推理框架，用于多目标视觉-语言导航	VLN
4	Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows	Agentics 2.0：提出逻辑转换代数，构建可靠、可扩展、可观测的Agentic数据工作流	large language model
5	CodeTaste: Can LLMs Generate Human-Level Code Refactorings?	CodeTaste：评估LLM在代码重构中能否达到人类水平，并提出改进方法	large language model
6	In-Context Environments Induce Evaluation-Awareness in Language Models	利用上下文环境诱导语言模型产生评估感知，揭示其潜在的策略性欠佳表现	instruction following
7	A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development	提出双螺旋治理框架，提升Agentic AI在WebGIS开发中的可靠性	large language model
8	Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions	提出RealPref基准，评估LLM在个性化用户交互中长期偏好跟随能力	large language model	✅
9	CAM-LDS: Cyber Attack Manifestations for Automatic Interpretation of System Logs and Security Alerts	提出CAM-LDS数据集，用于提升LLM在系统日志和安全警报中的网络攻击自动解释能力。	large language model
10	SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration	提出SWE-CI基准，评估LLM智能体在持续集成中维护代码库的能力	large language model
11	MACC: Multi-Agent Collaborative Competition for Scientific Exploration	提出MACC框架，用于研究多智能体在科学探索中的协作与竞争机制。	large language model
12	AI4S-SDS: A Neuro-Symbolic Solvent Design System via Sparse MCTS and Differentiable Physics Alignment	AI4S-SDS：基于稀疏MCTS和可微物理对齐的神经符号溶剂设计系统	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control	评估离线强化学习在随机网络控制中的鲁棒性，为6G网络提供算法选择指导	reinforcement learning offline RL offline reinforcement learning
14	MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation	MAGE：面向语言智能体的元强化学习，实现战略性探索与利用	reinforcement learning large language model	✅
15	Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling	提出ALTERNATING-MARL以解决多智能体强化学习中的观察约束问题	reinforcement learning
16	Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism	提出基于DEVS形式化和LLM的离散事件世界模型生成与评估方法	world model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页