cs.AI（2026-02-25）

📊 共 11 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#	题目	一句话要点	标签	🔗	⭐
1	When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models	量化大型语言模型中世界英语变体的文化标记擦除现象	large language model
2	One Brain, Omni Modalities: Towards Unified Non-Invasive Brain Decoding with Large Language Models	NOBEL：利用大语言模型实现统一的非侵入式脑解码	large language model
3	ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices	ProactiveMobile：用于提升移动设备主动智能的综合基准测试	large language model multimodal
4	Enhancing LLM-Based Test Generation by Eliminating Covered Code	提出一种基于消除已覆盖代码的LLM测试生成方法，提升复杂方法覆盖率	large language model
5	Revisiting RAG Retrievers: An Information Theoretic Benchmark	提出MIGRASCOPE，基于互信息的RAG检索器分析框架，用于评估和优化检索增强生成系统。	large language model
6	Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts	大型语言模型在算法代理与人类专家之间表现出不一致的偏见	large language model
7	Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem	Prompt架构显著影响推理质量：基于洗车问题的变量隔离研究	large language model
8	An Evaluation of Context Length Extrapolation in Long Code via Positional Embeddings and Efficient Attention	针对长代码补全，研究基于位置编码和高效注意力机制的上下文长度外推方法	large language model
9	Structurally Aligned Subtask-Level Memory for Software Engineering Agents	提出结构化对齐的子任务级记忆，提升软件工程Agent的长期推理能力	large language model
10	Beyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive Information	提出SemSIEdit框架，通过Agentic自校正降低LLM语义敏感信息泄露风险。	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	🔗	⭐
11	ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning	ARLArena：用于稳定Agentic强化学习的统一框架	reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页