cs.AI（2025-09-01）
📊 共 6 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Robix: A Unified Model for Robot Interaction, Reasoning and Planning | 提出Robix以解决机器人交互与任务规划问题 | reinforcement learning visual grounding chain-of-thought | ||
| 2 | VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use | 提出VerlTool以解决多轮工具交互的强化学习问题 | reinforcement learning | ✅ | |
| 3 | GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models | 提出GradeSQL：利用Outcome Reward Models提升大语言模型Text-to-SQL生成性能 | reinforcement learning large language model |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving | 提出动态推测解码引擎DSDE以解决大批量服务中的推测长度问题 | large language model | ||
| 5 | LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition | 提出LLM引导的语义关系推理方法，提升多模态意图识别性能 | large language model multimodal chain-of-thought | ✅ | |
| 6 | An LLM-enabled semantic-centric framework to consume privacy policies | 提出一种基于LLM的语义中心框架，用于解析隐私政策并构建知识图谱。 | large language model |