cs.AI（2025-10-19）

📊 共 8 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱一：机器人控制 (Robot Control) (1) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	DeepAnalyze: Agentic Large Language Models for Autonomous Data Science	DeepAnalyze：面向自主数据科学的Agentic大语言模型	large language model
2	BreakFun: Jailbreaking LLMs via Schema Exploitation	BreakFun：利用模式漏洞攻击大型语言模型	large language model chain-of-thought
3	SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models	SAKE：首个面向大型音频-语言模型听觉属性知识编辑的基准测试。	multimodal
4	Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations	揭示语音情感变化下大型语音语言模型（LALM）的安全漏洞	multimodal
5	When Many-Shot Prompting Fails: An Empirical Study of LLM Code Translation	揭示LLM代码翻译中多示例提示的悖论：少量胜过大量	large language model
6	Are LLMs Court-Ready? Evaluating Frontier Models on Indian Legal Reasoning	构建印度法律推理基准，评估LLM在法律领域的适用性	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
7	VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents	VAGEN：通过强化学习增强世界模型推理，提升多轮VLM Agent性能	manipulation reinforcement learning world model

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

#	题目	一句话要点	标签	🔗	⭐
8	A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications	综述：基于强化学习的Agentic Search，填补了该领域系统性研究的空白。	reinforcement learning large language model	✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页