cs.AI（2025-09-04）

📊 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) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 Schema Inference for Tabular Data Repositories Using Large Language Models 提出SI-LLM，利用大语言模型为表格数据仓库推断模式 large language model ✅
2 RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models RepoDebug：用于评估大型语言模型在仓库级多任务多语言调试能力的数据集 large language model
3 NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models NeuroBreak：揭示大型语言模型内部的越狱机制，提升安全性。 large language model
4 What Would an LLM Do? Evaluating Policymaking Capabilities of Large Language Models 评估大型语言模型在社会政策制定中的能力，以解决无家可归问题。 large language model
5 Towards Personalized Explanations for Health Simulations: A Mixed-Methods Framework for Stakeholder-Centric Summarization 提出一种混合方法框架，利用LLM为健康模拟提供个性化解释，满足不同利益相关者的需求。 large language model
6 Psychologically Enhanced AI Agents 提出MBTI-in-Thoughts框架以增强大型语言模型的心理效能 large language model
7 Enhancing Technical Documents Retrieval for RAG Technical-Embeddings：增强RAG技术文档检索的框架 large language model
8 Characterizing Fitness Landscape Structures in Prompt Engineering 通过自相关分析语义空间，揭示Prompt工程中适应度景观结构的特性 large language model
9 Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning 揭示中间语言对神经符号推理的影响，强调形式语言选择的重要性 large language model
10 NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings 提出NER Retriever，利用类型感知嵌入实现零样本命名实体检索。 large language model ✅
11 AutoPBO: LLM-powered Optimization for Local Search PBO Solvers AutoPBO：利用LLM优化局部搜索PBO求解器，提升求解性能 large language model
12 Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem 利用LLM Agent在El Farol酒吧问题中探索涌现的社会动态 large language model
13 Between a Rock and a Hard Place: Exploiting Ethical Reasoning to Jailbreak LLMs TRIAL：利用伦理推理破解大型语言模型的越狱攻击 large language model
14 FaMA: LLM-Empowered Agentic Assistant for Consumer-to-Consumer Marketplace FaMA：基于LLM的C2C电商平台智能助手，提升用户交互效率 large language model
15 Continuous Monitoring of Large-Scale Generative AI via Deterministic Knowledge Graph Structures 提出基于确定性知识图谱的大规模生成式AI持续监控方法 large language model
16 SasAgent: Multi-Agent AI System for Small-Angle Scattering Data Analysis 提出SasAgent以自动化小角散射数据分析 large language model
17 SAMVAD: A Multi-Agent System for Simulating Judicial Deliberation Dynamics in India SAMVAD：用于模拟印度司法审议动态的多智能体系统 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
18 A Foundation Model for Chest X-ray Interpretation with Grounded Reasoning via Online Reinforcement Learning DeepMedix-R1：基于在线强化学习的胸部X光片可解释性基础模型 reinforcement learning foundation model
19 CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning 提出CoT-Space框架，用强化学习提升LLM的链式思考推理能力 reinforcement learning large language model chain-of-thought ✅
20 World Model Implanting for Test-time Adaptation of Embodied Agents 提出WorMI框架，通过世界模型植入实现具身智能体测试时自适应 world model embodied AI large language model
21 The Physical Basis of Prediction: World Model Formation in Neural Organoids via an LLM-Generated Curriculum 利用LLM生成课程，在神经类器官中构建世界模型的物理基础研究 reinforcement learning world model large language model
22 Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent 提出Meta-Policy Reflexion，提升LLM Agent在复杂任务中的效率与泛化性 reinforcement learning large language model multimodal
23 Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning 提出MPDF框架，通过元策略协作提升Agentic LLM在复杂推理任务中的性能。 reinforcement learning large language model
24 Decoupled Entity Representation Learning for Pinterest Ads Ranking 提出解耦实体表示学习框架，提升Pinterest广告排序效果 representation learning
25 Hybrid Reinforcement Learning and Search for Flight Trajectory Planning 提出混合强化学习与搜索的飞行轨迹规划方法，加速紧急情况下的航线重规划。 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
26 EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation EvoEmo：面向多轮价格谈判中对抗性LLM智能体的演化情感策略 manipulation reinforcement learning large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页