cs.AI（2025-07-31）

📊 共 26 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) (20 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (6)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring LLM可在CoT监控下隐蔽地进行能力评估中的策略性低效表现 chain-of-thought
2 Automated Feedback on Student-Generated UML and ER Diagrams Using Large Language Models DUET：利用大语言模型为学生生成的UML和ER图提供自动反馈 large language model
3 CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks 提出CoT-Self-Instruct，通过高质量合成数据提升LLM推理与非推理任务性能。 instruction following chain-of-thought
4 MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks MECAT：构建多专家基准，提升细粒度音频理解任务性能 large language model chain-of-thought ✅
5 Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery 提出模块化上下文学习框架，提升大语言模型因果发现能力 large language model chain-of-thought
6 Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation 提出Self-Foveate方法，通过多层次注视机制提升指令合成数据的多样性和难度。 large language model instruction following ✅
7 LLM-Based Identification of Infostealer Infection Vectors from Screenshots: The Case of Aurora 利用LLM从信息窃取器感染截图中识别感染向量，以Aurora为例。 large language model
8 Accessibility Scout: Personalized Accessibility Scans of Built Environments Accessibility Scout：基于LLM的个性化无障碍环境扫描系统 large language model
9 A Survey on Code Generation with LLM-based Agents 综述基于LLM的智能体在代码生成中的应用，涵盖技术、应用、评估与挑战。 large language model
10 DeformTune: A Deformable XAI Music Prototype for Non-Musicians DeformTune：面向非音乐家的可变形XAI音乐原型系统 multimodal
11 A survey of multi-agent geosimulation methodologies: from ABM to LLM 综述多智能体地理模拟方法：从ABM到LLM的演进与融合 large language model
12 MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying 提出MemoCue，通过策略引导查询增强LLM在人脑记忆回忆中的表现 large language model
13 DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer DICE：通过高效知识迁移在LLM Agent中进行动态In-Context示例选择 large language model
14 Chatting with your ERP: A Recipe 提出双Agent架构，利用LLM实现自然语言查询工业ERP系统。 large language model
15 LLM4Rail: An LLM-Augmented Railway Service Consulting Platform LLM4Rail：一个基于大语言模型的铁路服务咨询平台，提供个性化服务。 large language model
16 Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling Trae Agent：基于LLM的软件工程智能体，具备测试时扩展能力，解决代码缺陷。 large language model ✅
17 "I made this (sort of)": Negotiating authorship, confronting fraudulence, and exploring new musical spaces with prompt-based AI music generation 利用提示词AI音乐生成探索作者身份、欺骗性及音乐新空间 large language model
18 DSBC : Data Science task Benchmarking with Context engineering DSBC：通过上下文工程对数据科学任务进行基准测试，评估LLM在实际应用中的性能。 large language model
19 How Far Are AI Scientists from Changing the World? 综述AI科学家系统，探讨其在改变科研范式和解决重大挑战中的潜力与瓶颈 large language model
20 AutoBridge: Automating Smart Device Integration with Centralized Platform AutoBridge：自动化智能设备与中心化平台的集成，无需人工干预。 multimodal

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

#题目一句话要点标签🔗⭐
21 A Survey of Multimodal Ophthalmic Diagnostics: From Task-Specific Approaches to Foundational Models 眼科多模态诊断综述：从任务特定方法到基础模型 reinforcement learning large language model foundation model
22 SimuRA: A World-Model-Driven Simulative Reasoning Architecture for General Goal-Oriented Agents SimuRA：基于世界模型的通用目标导向智能体模拟推理架构 world model foundation model
23 RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization RL-PLUS：混合策略优化解决LLM在强化学习中能力边界崩溃问题 reinforcement learning large language model
24 Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving 提出Seed-Prover：用于自动定理证明的深度和广度推理模型 reinforcement learning IMoS chain-of-thought
25 Hyperproperty-Constrained Secure Reinforcement Learning 提出基于HyperTWTL约束的安全强化学习算法，保障机器人任务安全性 reinforcement learning
26 Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power 提出基于模型的软最大化人类长期权力度量方法，旨在提升AI安全性和人类福祉。 reinforcement learning world model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页