【赞助商】
OpenClaw快报
每天五分钟,听听 OpenClaw 快报,带你了解最新动态和业内讨论
传送门 www.xiaoyuzhoufm.com
【目录】
本期的 15 篇论文如下:
[] 🤖 Apodex 1.1: Scaling Agentic Intelligence for Complex Work(Apodex 1.1:扩展智能体智能以应对复杂工作)
[] 🎮 EchoWM: Open and Enterable Omnimodal World Models(EchoWM:开放且可进入的全模态世界模型)
[] 🛒 TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming(TLive-Omni:面向电商直播的全模态理解模型)
[] 🎨 Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision(通过概念缩放与密集监督解锁图像编辑的潜力)
[] 📱 MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks(MobilePA-Bench:面向复杂真实世界任务的移动规划智能体基准评测)
[] 🤖 Prime Agent: A Self-Improving RLM Harness(Prime Agent:一种自我改进的递归语言模型工具框架)
[] 🧊 Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion(Block3D:通过块状扩散的高效文本到三维生成)
[] 🚗 RISE: Adaptive Imagination for World Action Models(RISE:面向世界行动模型的自适应想象)
[] 📈 Towards a Densing Law for User Representation Learning at Billion-Scale Capacity(面向十亿级容量用户表示学习的稠密化定律)
[] ⚖ ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction(ARC:开放式真实世界交互中的公平相对优势比较)
[] 🧠 ReWorld: An Interactive World Model with Long-Horizon Memory(ReWorld:一个具有长时记忆的交互式世界模型)
[] ⚖ Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization(超越稳定性-探索困境:面向大语言模型策略优化的环境正则化)
[] 🎮 GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?(GameXpert-Bench:编码智能体距离专家级游戏开发还有多远?)
[] 🧪 One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows(一次成功不等于可靠:Thinkingbox——面向有状态业务工作流的智能体沙盒与基准测试)
[] 🎯 Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection(Task-CoEvolve:通过自适应验证任务选择实现高效的工具链优化)

【关注我们】
您还可以在以下平台找到我们,获得播客内容以外更多信息
小红书: AI速递
