cs.AI（2025-09-05）

📊 共 25 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#	题目	一句话要点	标签	🔗	⭐
1	The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models	研究大型语言模型中的“退出对话”偏好，揭示模型在不同情境下的退出行为。	large language model
2	Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models	提出伪装越狱提示基准测试，评估大语言模型在隐蔽对抗攻击下的安全性	large language model
3	Scaling Performance of Large Language Model Pretraining	揭秘LLM预训练：探索分布式训练、大数据管理及数据并行扩展策略	large language model
4	Authorship Without Writing: Large Language Models and the Senior Author Analogy	类比资深作者：探讨大型语言模型在学术写作中的作者身份问题	large language model
5	REMOTE: A Unified Multimodal Relation Extraction Framework with Multilevel Optimal Transport and Mixture-of-Experts	提出REMOTE框架，通过多层最优传输和混合专家模型实现统一的多模态关系抽取。	multimodal	✅
6	A Federated Fine-Tuning Paradigm of Foundation Models in Heterogenous Wireless Networks	提出一种异构无线网络下联邦微调基础模型的在线优化框架，提升模型精度和能效。	foundation model
7	User Privacy and Large Language Models: An Analysis of Frontier Developers' Privacy Policies	分析前沿AI开发商隐私政策，揭示LLM用户数据被用于模型训练的现状与风险。	large language model
8	SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing	提出SparkUI-Parser，通过稳健的坐标定位和解析增强GUI感知能力。	large language model multimodal	✅
9	Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts	提出一种基于本体的对话描述方法，以提升大型语言模型作为对话代理的可控性。	large language model
10	VoltanaLLM: Feedback-Driven Frequency Control and State-Space Routing for Energy-Efficient LLM Serving	VoltanaLLM：面向节能LLM服务的反馈驱动频率控制与状态空间路由	large language model	✅
11	Combining TSL and LLM to Automate REST API Testing: A Comparative Study	提出RestTSLLM，结合TSL与LLM自动化REST API测试用例生成。	large language model
12	LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithm	提出基于LLM的实例驱动启发式偏置BRKGA算法，解决NP难的最长运行子序列问题。	large language model
13	Differential Robustness in Transformer Language Models: Empirical Evaluation Under Adversarial Text Attacks	评估Transformer语言模型在对抗文本攻击下的鲁棒性差异	large language model
14	AI Agents for Web Testing: A Case Study in the Wild	提出WebProber，利用AI Agent进行Web测试，发现传统方法难以检测的可用性问题。	large language model
15	GenAI-based test case generation and execution in SDV platform	提出基于GenAI的测试用例生成与执行方法，加速SDV平台验证。	large language model
16	LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual-Loop Edge-Terminal Collaboration	提出基于LLM的多智能体双环协同框架，提升6G网络边缘终端任务处理效率	large language model
17	Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents	提出DOVIS协议和AgentRank-UC算法，实现Web of Agents中Agent的动态排名。	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	🔗	⭐
18	TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models	提出TalkToAgent，利用LLM实现人机交互式强化学习智能体解释	reinforcement learning large language model
19	What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking	提出WiA-LLM，利用主动思考进行大型语言模型在MOBA游戏中的假设分析。	reinforcement learning world model large language model
20	Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents	提出基于LLM驱动的分层脚手架，用于具身智能体的生成世界模型	reinforcement learning world model large language model
21	Learning-Based Planning for Improving Science Return of Earth Observation Satellites	提出基于学习的地球观测卫星规划方法，提升科学数据回报率	reinforcement learning imitation learning
22	Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework	提出Sticker-TTS，利用历史经验提升大模型在数学推理任务中的测试时性能。	reinforcement learning imitation learning	✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
23	LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation	LatticeWorld：多模态大语言模型驱动的交互式复杂世界生成框架	sim-to-real world model embodied AI
24	OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration	提出OSC框架，通过动态知识对齐增强多Agent LLM协作中的认知协同	OSC large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
25	Exploring Situated Stabilities of a Rhythm Generation System through Variational Cross-Examination	通过变异交叉检验探索GrooveTransformer节奏生成系统的多重稳定性	affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页