cs.AI（2025-07-12）

📊 共 9 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱一：机器人控制 (Robot Control) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Enhancing Interpretability in Software Change Management with Chain-of-Thought Reasoning	提出SCELM框架，利用链式思考提升软件变更管理的可解释性与效率	chain-of-thought
2	Learning from Synthetic Labs: Language Models as Auction Participants	利用大型语言模型模拟拍卖参与者，降低拍卖研究成本	large language model chain-of-thought
3	LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to Spearphishing	提出LLM-Stackelberg博弈框架，用于建模LLM参与的序贯决策，并应用于鱼叉式网络钓鱼。	large language model
4	LLM-Powered Quantum Code Transpilation	提出基于LLM的量子代码转译方法，提升跨平台量子软件开发效率。	large language model
5	Knowledge Conceptualization Impacts RAG Efficacy	知识概念化影响RAG效果：探究知识表示对Agentic RAG系统性能的影响	large language model
6	SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation	SPICE：自动化SWE-bench标注流水线，提升问题清晰度、测试覆盖率和工作量评估。	foundation model
7	AInsight: Augmenting Expert Decision-Making with On-the-Fly Insights Grounded in Historical Data	AInsight：利用历史数据实时洞察，增强专家决策能力	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Hide-and-Shill: A Reinforcement Learning Framework for Market Manipulation Detection in Symphony-a Decentralized Multi-Agent System	提出Hide-and-Shill框架，用于检测去中心化金融（DeFi）中的市场操纵行为。	manipulation reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
9	EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique	EduFlow：通过多阶段、多视角评判提升MLLM的问题解决能力	curriculum learning teacher-student large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页