一个外壳把AI推理成功率从30%拉到95%
大模型本身只是顺序读字的机器，真正干长活靠的是外面那层壳。Prime Agent 就是这层壳：它给模型配一个常驻的 Python 终端、让多个子智能体直接互相说话、把每次任务的记忆和技能都存下来。结果很夸张——在 ARC-AGI-3 推理基准上，同一个模型套上这层壳，最佳成绩从 30% 飙到 95.5%。换句话说，模型没变，变的是它干活的环境。这不是你明天能装上的东西，但它说明一件事：AI 能力的瓶颈，可能不在模型脑子里，而在它周围那圈脚手架。
📄 原文摘要(英文)
Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. A persistent IPython REPL follows the Recursive Language Model abstraction for programmatic context processing and test-time compute, while Continual Harness preserves histories, memories, skills, prompts, and subagent specifications across trajectories. Recursive subagents coordinate through direct agent-to-agent communication, and the Agents View lets humans inspect and manage daemon-backed sessions. Prime Agent standardizes execution, recovery, verification, and resource accounting while leaving strategy construction to the model. This low-friction, expressive membrane prevents harness failures from becoming model failures and pushes measurement toward the model's true maximal underlying capability. Prime Agent raises ARC-AGI-3 RHAE Best@1 from 30% to 95.5% and matches or exceeds native and popular harnesses across long-context coding, GPU-kernel generation, emulator construction, and autonomous nanoGPT speedruns. On Factorio, we find refinement allows for continuous technology progression and dedicated subagents enable parallelized work. Code is available at https://github.com/PrimeIntellect-ai/prime-agent.