DeepSeek和GLM用JIT-Agent后性能大幅超越GPT-5.6，还能动态生成智能体框架并自我进化。
JIT-Agent是一种新型模型，其输出为智能体框架。该模型采用固定四模块协议（内存、规划、动作协议和工具编排）将框架形式化为可组合工件，可为任何现成智能体LLM即时合成框架。JIT-Agent还可在执行过程中修复框架，并通过从不断扩展的先前配置档案中提炼性能信号实现自我进化。在DeepSearchQA基准上，搭载JIT-Agent的DeepSeek-V4-Flash比GPT-5.6高9.1分，在OdysseyBench上高4.3分，GLM-5.2最多提升20.2分。
If you maintain a hand-built agent harness, this one is worth your time. (bookmark it) I feel like...
If you maintain a hand-built agent harness, this one is worth your time. (bookmark it) I feel like everyone is sleeping on the idea of dynamically generating agent harnesses on the fly. As you aim to own your harness, this is a topic more devs will lean into. Here is a great report discussing this topic. JIT-Agent is a model whose output is an agent harness. It formalizes the harness as a composable artifact under a fixed four-module protocol covering memory, planning, action protocol, and tool orchestration, then synthesizes one on the fly for any off-the-shelf agentic LLM. It also repairs harnesses mid-execution and self-evolves by distilling performance signals from an expanding archive of prior configurations. With JIT-Agent attached, DeepSeek-V4-Flash surpasses GPT-5.6 on DeepSearchQA (+9.1) and OdysseyBench (+4.3). GLM-5.2 gains up to +20.2 points. The generated harnesses are also performance-competitive with mature runtimes like OpenCode and Claude Code. Paper: arxiv.org/abs/2608.25593 Chat with Paper: academy.dair.ai/papers/jit-age… 💬 4 🔄 2 ❤️ 14 👀 1737 📊 8 ⚡