openJiuwen框架让代理能力在运行时动态调整，性能超越现有方案，开发者可自由组装代理组件。
openJiuwen是一个开源代理框架，解决了传统静态编码代理框架的局限性。该框架在SWE-bench Verified基准上达到82.6%，在Terminal-Bench 2.1上达到87.19%，领先官方排行榜最高分3.4和3.39个百分点。框架采用基于Rail的组成方式，允许开发者组装单个代理、委托子代理和群体流。运行时证据会动态重塑上下文、反馈和任务控制，同时保持模型策略固定。
Nice paper showing just how far you can push an agent harness. In most setups, the default coding a...
Nice paper showing just how far you can push an agent harness. In most setups, the default coding agent harness is static. Capabilities get wired in at design time, and the run has no way to change how it is being executed. openJiuwen is an open-source harness built to fix that. It reaches 82.6% on SWE-bench Verified and 87.19% on Terminal-Bench 2.1, ahead of the strongest official leaderboard entries by 3.4 and 3.39 points. A bit on how openJiuwen works: Rail-based composition lets developers assemble single agents, delegated sub-agents and swarm flows over one shared execution substrate. Runtime evidence from semantic diagnostics, execution outcomes and task progress then reshapes context, feedback and task control while the run is still going. The model policy stays fixed throughout, so the gains are attributable to the harness rather than to the model underneath it. Paper: arxiv.org/abs/2608.27969 Chat with Paper: academy.dair.ai/papers/openjiu… 💬 3 🔄 1 ❤️ 20 👀 3428 📊 8 ⚡