cs.AI（2025-08-13）

📊 共 21 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization 提出长度控制偏好优化以解决大规模推理模型的效率问题 chain-of-thought
2 Mathematical Computation and Reasoning Errors by Large Language Models 评估大型语言模型在数学计算中的错误以提升教育效果 large language model
3 Exploring the Potential of Large Language Models in Fine-Grained Review Comment Classification 利用大型语言模型提升代码审查评论分类的准确性 large language model
4 An Automated Multi-modal Evaluation Framework for Mobile Intelligent Assistants Based on Large Language Models and Multi-Agent Collaboration 提出自动化多模态评估框架以解决智能助手评估问题 large language model
5 Using Artificial Intuition in Distinct, Minimalist Classification of Scientific Abstracts for Management of Technology Portfolios 提出人工直觉方法以实现科学摘要的高效分类 large language model
6 KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems 提出KompeteAI以解决AutoML系统的执行瓶颈与探索不足问题 large language model
7 Agentic AI Frameworks: Architectures, Protocols, and Design Challenges 系统评估Agentic AI框架以解决智能代理通信问题 large language model
8 Amazon Nova AI Challenge -- Trusted AI: Advancing secure, AI-assisted software development 通过Amazon Nova AI Challenge推动安全AI辅助软件开发 large language model
9 Profile-Aware Maneuvering: A Dynamic Multi-Agent System for Robust GAIA Problem Solving by AWorld 提出动态多智能体系统以增强GAIA问题求解的鲁棒性 large language model
10 The PacifAIst Benchmark:Would an Artificial Intelligence Choose to Sacrifice Itself for Human Safety? 提出PacifAIst基准以解决AI自我优先行为评估问题 large language model
11 UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-Judge 提出UDA框架以解决大语言模型评估中的偏见问题 large language model
12 On Negative-aware Preference Optimization for Recommendation 提出负样本感知偏好优化方法以提升推荐系统性能 large language model
13 AmbiGraph-Eval: Can LLMs Effectively Handle Ambiguous Graph Queries? 提出AmbiGraph-Eval以评估LLMs处理模糊图查询的能力 large language model
14 Your Coding Intent is Secretly in the Context and You Should Deliberately Infer It Before Completion 提出三阶段推理框架以提升代码补全的准确性 large language model
15 Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesis 提出AI辅助数据提取方法以提高知识综合的准确性和效率 large language model
16 Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference 提出KV-Cloak以解决LLM推理中的KV缓存隐私风险问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
17 Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation 提出VIPCGRL以解决人类中心的程序内容生成问题 reinforcement learning deep reinforcement learning contrastive learning
18 Centralized Permutation Equivariant Policy for Cooperative Multi-Agent Reinforcement Learning 提出集中置换等变策略以解决多智能体强化学习中的性能瓶颈 reinforcement learning
19 MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement 提出MEML-GRPO以解决RLVR中的奖励稀疏问题 reinforcement learning large language model
20 EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making 提出EvoCurr以解决复杂决策问题的学习效率 curriculum learning large language model
21 Extending the Entropic Potential of Events for Uncertainty Quantification and Decision-Making in Artificial Intelligence 提出事件熵势以增强人工智能中的不确定性量化与决策能力 reinforcement learning reward design

⬅️ 返回 cs.AI 首页 · 🏠 返回主页