cs.AI（2025-06-05）

📊 共 27 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 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 Sensory-Motor Control with Large Language Models via Iterative Policy Refinement 提出一种方法使大型语言模型控制具身智能体 large language model
2 StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models 提出StealthInk以解决大语言模型水印识别问题 large language model
3 Benchmarking Large Language Models on Homework Assessment in Circuit Analysis 基于大语言模型的电路分析作业评估基准研究 large language model
4 Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion 提出Exp4Fuse框架以提升稀疏检索性能 large language model
5 E-bike agents: Large Language Model-Driven E-Bike Accident Analysis and Severity Prediction 提出基于大语言模型的电动自行车事故分析与严重性预测方法 large language model
6 When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models 提出策略性欺骗检测方法以解决大型语言模型的诚实性问题 large language model chain-of-thought
7 Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists 提出MAPPS框架以实现更高自主性的材料发现 large language model foundation model
8 ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation 提出ScaleRTL以解决RTL代码生成中的数据瓶颈问题 large language model chain-of-thought
9 Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation 提出GUI-Critic-R1模型以解决GUI自动化中的预操作错误诊断问题 large language model multimodal
10 OpenAg: Democratizing Agricultural Intelligence 提出OpenAg以解决农业智能化不足问题 large language model foundation model
11 MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark 提出MMTU基准以解决表格理解与推理的评估问题 foundation model ✅
12 Deployability-Centric Infrastructure-as-Code Generation: An LLM-based Iterative Framework 提出基于LLM的IaC生成框架以解决部署能力不足问题 large language model
13 Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety 提出统一框架以提升大语言模型的安全性与可解释性 large language model
14 Teaming in the AI Era: AI-Augmented Frameworks for Forming, Simulating, and Optimizing Human Teams 提出AI增强框架以优化人类团队形成与表现 large language model
15 From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law 通过明确拒绝提升大型语言模型与国际人道法的对齐 large language model
16 LLM-First Search: Self-Guided Exploration of the Solution Space 提出LLM-First Search以解决搜索策略固定性问题 large language model ✅
17 Sentinel: SOTA model to protect against prompt injections 提出Sentinel以防御提示注入攻击 large language model
18 On Automating Security Policies with Contemporary LLMs 提出基于大型语言模型的自动化安全策略合规框架 large language model
19 GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval 提出GOLFer以解决小型语言模型生成文档的幻觉问题 large language model
20 Intelligent Channel Allocation for IEEE 802.11be Multi-Link Operation: When MAB Meets LLM 提出BAI-MCTS与LLM-BAI-MCTS以解决WiFi 7动态信道分配问题 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🔗⭐
21 Safe Planning and Policy Optimization via World Model Learning 提出一种新型模型驱动强化学习框架以解决安全性与性能优化问题 reinforcement learning world model model-based RL
22 Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning 提出自适应长度惩罚以提高推理效率 reinforcement learning
23 Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation 提出R2Rec以解决推荐系统中隐式反馈的推理问题 reinforcement learning large language model
24 Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning 提出SPARKLE框架以深入理解RL对LLMs推理能力的影响 reinforcement learning ✅
25 Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling 提出基于大语言模型的代理模型以解决MMO经济模拟中的人类行为仿真问题 reinforcement learning large language model
26 Constructive Symbolic Reinforcement Learning via Intuitionistic Logic and Goal-Chaining Inference 提出基于直觉逻辑和目标链推理的构造性符号强化学习框架 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
27 Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework 提出一种新框架以解决偏见和操控问题 manipulation preference learning RLHF

⬅️ 返回 cs.AI 首页 · 🏠 返回主页