给AI换副好骨架，比换大脑更管用
大模型的能力不只看模型本身，外围那套「怎么用」的框架——记什么、怎么规划、调什么工具——往往贡献更大。但过去这套框架全靠人手工搭，换个任务就得重来。JIT-Agent 把「搭框架」本身变成一种可训练的智能：它能在任务到来时现场生成适配的框架，跑崩了还能自己修，并且从历史配置里不断进化。装上它，DeepSeek-V4-Flash 在两项评测上反超了更强的 GPT-5.6，GLM-5.2 最高涨了 20 分。这不是你明天能用的产品，但它指出了一个方向：AI 的进步未必只靠堆模型参数，把「怎么用」这件事自动化，可能是另一条同样陡峭的曲线。
📄 原文摘要(英文)
Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying foundation model. Yet harness design remains manual, task-specific, and fundamentally unscalable. We present JIT-Agent, a harness intelligence model trained to synthesize task-adaptive agent harnesses on the fly for arbitrary off-the-shelf agentic LLMs. We formalize the agent harness as a composable, machine-generatable artifact governed by a fixed four-module protocol, and train JIT-Agent to customize harnesses for a given task at hand, repair harnesses for stable and reliable execution, and self-evolve by distilling performance signals from an expanding archive of prior harness configurations. Equipped with JIT-Agent as a harness helper, DeepSeek-V4-Flash surpasses GPT-5.6 on DeepSearchQA (+9.1) and OdysseyBench (+4.3), while the already strong GLM-5.2 gains up to +20.2 points. Across controlled evaluations, JIT-Agent-generated harnesses are performance-competitive with mature agent runtimes such as OpenCode and Claude Code and consistently improve multi-scale model families of DeepSeek V4, Mimo-V2.5, and Qwen3.6. To our knowledge, JIT-Agent is the first model purpose-built for just-in-time harness generation, establishing harness intelligence as a trainable, transferable, and compounding dimension of agent capability orthogonal to model scaling.