cs.AI（2026-04-15）

📊 共 15 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Large Language Models to Enhance Business Process Modeling: Past, Present, and Future Trends 利用大型语言模型增强业务流程建模：综述现有方法并展望未来趋势 large language model
2 [Emerging Ideas] Artificial Tripartite Intelligence: A Bio-Inspired, Sensor-First Architecture for Physical AI 提出人工三方智能ATI架构，解决物理AI中传感器与推理协同优化问题 embodied AI foundation model
3 GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis GeoAgentBench：用于空间分析中工具增强型Agent的动态执行基准测试 large language model multimodal
4 The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents 提出认知伴侣架构，用于检测和恢复LLM Agent中的推理退化问题 large language model
5 TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration TREX：通过Agent驱动的树状探索实现LLM微调自动化 large language model
6 MIND: AI Co-Scientist for Material Research 提出MIND：一个基于LLM的材料研究AI协同科学家框架 large language model ✅
7 Weight Patching: Toward Source-Level Mechanistic Localization in LLMs 提出权重修补方法，用于定位LLM中源级别的机制性行为。 instruction following
8 The Cognitive Circuit Breaker: A Systems Engineering Framework for Intrinsic AI Reliability 提出认知断路器框架，通过监测模型内在认知失调提升LLM可靠性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
9 Towards Scalable Lightweight GUI Agents via Multi-role Orchestration LAMO：面向轻量级GUI代理的多角色协同框架，提升任务可扩展性 reinforcement learning distillation large language model
10 Reward Design for Physical Reasoning in Vision-Language Models 针对视觉语言模型物理推理，提出基于GRPO的奖励函数设计方法 reward design
11 Hierarchical Reinforcement Learning with Runtime Safety Shielding for Power Grid Operation 提出运行时安全屏蔽的分层强化学习方法，用于电力系统运行控制。 reinforcement learning
12 RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management RiskWebWorld：电商风控GUI智能体的真实交互基准 reinforcement learning foundation model
13 Learning from Change: Predictive Models for Incident Prevention in a Regulated IT Environment 提出一种基于LightGBM的可解释IT变更风险预测模型，用于金融等监管环境下的事件预防。 predictive model
14 Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt 提出音频侧时间提示以解决音频语言模型的时间感知问题 reinforcement learning TAMP

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 Secure and Privacy-Preserving Vertical Federated Learning 提出一种安全且保护隐私的垂直联邦学习框架，适用于不同部署场景。 MPC

⬅️ 返回 cs.AI 首页 · 🏠 返回主页