cs.AI（2026-07-22）

📊 共 16 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) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Silent Failures in Multimodal Agentic Search:A Diagnostic Taxonomy and Cross-Judge Evaluation 提出六类分类法以诊断多模态智能搜索中的隐性失败问题 multimodal ✅
2 Symbol and Footprint Database for Electronic Components by Agentic Recognition and Generation 提出SFgen以解决电子元件符号和封装生成问题 large language model multimodal
3 HijackKV: New Threat in Position-Independent KV Cache Reuse 提出HIJACKKV以解决KV缓存重用中的安全威胁 large language model
4 FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense 提出FedLSG以解决联邦图神经网络的后门攻击问题 large language model
5 PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity 提出PoTRE框架以解决复杂推理问题 large language model
6 Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis 提出小型语言模型协同分析以提升恶意软件检测效果 large language model
7 PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning 提出PRO-LONG以解决长时间推理任务中的记忆管理问题 large language model ✅
8 Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model 提出材料科学机制的开放权重语言模型解析方法 large language model
9 When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Markets 通过信息设计降低大型语言模型介导的货运市场集中度 large language model
10 SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data 提出SenWorld以解决智能助手评估数据缺乏的问题 large language model
11 Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes 提出CoHarden框架以解决BRT生成中的修复成功率问题 large language model
12 An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports 提出自动化框架以提取可达攻击链解决网络威胁情报报告问题 large language model
13 PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization 提出PerfAgent以解决代码优化中的性能瓶颈问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
14 Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering 提出统一的全曲生成框架以解决音乐创作多样性问题 flow matching DPO

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 The Ethics of Autonomous AI Agents for Offensive Security 分析自主AI代理在进攻安全中的伦理问题 penetration

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations 提出DocOps框架以解决自主智能体在文档操作中的局限性 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页