cs.AI（2026-07-01）

📊 共 19 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) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments 提出SenseWalk以解决语义轨迹模拟中的数据收集与技术门槛问题 large language model
2 LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution 提出LLVM-Bench以解决LLVM编译器问题的评估与进展 large language model
3 NeuroCogMap Reveals Cognitive Organization of Large Language Models 提出NeuroCogMap以揭示大语言模型的认知组织结构 large language model
4 Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains 提出Agent Skill Supply Chains以解决技能依赖管理问题 large language model
5 Agentic generation of verifiable rules for deterministic, self-expanding reaction classification 提出全自动化多代理框架以解决化学反应分类问题 large language model
6 Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows 提出分析工作流中的语义差距解决方案 large language model
7 Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences 提出RefChecker以解决学术论文引用虚假问题 large language model ✅
8 Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces 提出SMT框架以解决大型语言模型的安全漏洞问题 large language model ✅
9 Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval 提出基于LLM聚类的实时困难负样本采样以提升检索效果 large language model
10 PHREEQC-MCQ-200: A Diagnostic Benchmark for Tool-Augmented Scientific Simulator Agents 提出PHREEQC-MCQ-200基准以评估工具增强的科学模拟器代理 large language model
11 An LLM-Based Framework for Intent-Driven Network Topology Design 提出基于大语言模型的框架以解决网络拓扑设计问题 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🔗⭐
12 AGI Maze as a Benchmark Framework for World-Modeling Agents 提出AGI Maze框架以解决世界建模代理的评估问题 world model world models large language model
13 Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments 提出MuSix框架以解决多尺度知识适应问题 world model world models
14 Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination 提出Graph-PRefLexOR以解决科学假设生成的可追溯性问题 reinforcement learning large language model
15 Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis 提出统一引导框架以提升语音合成的效率与鲁棒性 flow matching classifier-free guidance
16 Diffusion-GR2: Diffusion Generative Reasoning Re-ranker 提出Diffusion-GR2以解决生成推理重排序的效率问题 reinforcement learning distillation chain-of-thought
17 Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use 提出OpenAgent以解决工具使用中的开放世界泛化问题 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 Coachable agents for interactive gameplay 提出教练代理以实现交互式游戏中的风格控制 humanoid reinforcement learning foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
19 A Multi-Resolution Finite-Volume Inspired Deep Learning Framework for Spatiotemporal Dynamics Prediction 提出MuRFiV框架以解决复杂时空动态预测问题 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页