cs.AI（2025-05-26）

📊 共 13 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) (11 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2)

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

#	题目	一句话要点	标签	🔗	⭐
1	On Path to Multimodal Historical Reasoning: HistBench and HistAgent	提出HistBench历史推理基准和HistAgent，提升AI在历史领域的多模态理解能力。	generalist agent large language model multimodal
2	ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows	ScienceBoard：构建多模态自主Agent的科学工作流评估基准	large language model multimodal	✅
3	Project Riley: Multimodal Multi-Agent LLM Collaboration with Emotional Reasoning and Voting	Project Riley：提出一种基于情感推理和投票的多模态多智能体LLM协作框架	large language model multimodal
4	Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution	提出Alita以解决现有智能体适应性不足的问题	generalist agent large language model	✅
5	Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program	利用大型语言模型作为Kerbal太空计划中的自主航天器操作员	large language model	✅
6	From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data	BALSa：利用合成数据引导音频-语言对齐，提升ALLM性能并缓解幻觉问题	large language model instruction following
7	Ten Principles of AI Agent Economics	提出AI Agent经济学十大原则，旨在负责任地将AI Agent整合到人类社会经济系统中。	multimodal
8	Capability-Based Scaling Laws for LLM Red-Teaming	提出基于能力的LLM红队攻防扩展法则，预测攻击成功率	large language model
9	StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs	StructEval：全面评估LLM生成结构化输出能力的基准测试	large language model
10	DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph	提出DCG-SQL，通过深度上下文Schema链接图增强Text-to-SQL的上下文学习能力	large language model	✅
11	HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation	提出HS-STaR，通过分层采样提升自训练推理器在数学问题上的学习效率	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
12	SCAR: Shapley Credit Assignment for More Efficient RLHF	SCAR：基于Shapley值的信用分配方法，提升RLHF训练效率	reinforcement learning RLHF large language model
13	MultiPhishGuard: An LLM-based Multi-Agent System for Phishing Email Detection	提出MultiPhishGuard，一种基于LLM多智能体系统的钓鱼邮件检测方法	reinforcement learning chain-of-thought

⬅️ 返回 cs.AI 首页 · 🏠 返回主页