8月25日
05:35
05:35elvis@omarsar0
精选
Speculative Programmatic Tool Calling (sPTC) is a new technique for optimizing harness designs in code generation, offering 1 to 1.2x speedup by overlapping tool calls with token generation. It's developed by the same author as RLM and aims to improve efficiency at the harness layer.
推荐理由:Check out Speculative Programmatic Tool Calling (sPTC) for a fresh approach to harness optimization, offering significant speedup compared to traditional methods. It's a must-read for those interested in RLM and harness efficiency.
7月2日
00:38
00:38官方账号LangChain@LangChainAI
LangChain 的 Deep Agents 新增了递归语言模型(RLM)工作流功能。Sydney Runkle 用 6 分钟视频讲解其原理和用法。RLM 允许 Agent 在多个轮次中递归调用语言模型,提升复杂任务的表现。该功能已集成到 Deep Agents 的当前版本中。
推荐理由:LangChain 给 Deep Agents 加了 RLM 工作流,能递归调用语言模型做更复杂的事。6 分钟视频讲得很清楚,可以看看。