将大模型智能行为编译为可验证的高效程序，实现低成本重复使用。
Auto: The AGI Compiler
- 记录并分析智能体行为，提取确定性部分生成可验证代码
- 在300条任务流上实现每项成本从59降至2微美元（6.4倍提升）
- 适合关注推理效率与可靠性保障的系统开发者
每个大模型智能体运行时都需逐标记重新推导行为：高效但昂贵、缓慢且无界。我们提出Auto，一个编译器，能记录实时智能体行为，测量其中隐藏的确定性部分，将其提取为经验证的程序或精简专家，并输出带有量化保证的认知二进制文件——这些WebAssembly产物的声明能力由沙箱物理强制执行。分层运行时在合规校准的保护下执行已编译行为；保护触发时退回到参考智能体，捕获轨迹重新编译，确保不重复计算。我们以狭义可测试方式定义‘AGI编译器’：能自主将新经验转化为永久、可验证、近乎免费的技能，同时测量未知内容。在我们引入并预先注册的AUTO-BENCH基准上，560个记录的前沿智能体片段中87.1%为可观测确定性（四类任务中有三类达100.0%）。在包含三次分布偏移的300项任务流上，闭环编译出三代产物，边际成本从59微美元降至2微美元（端到端提升6.4倍），对可观测输入保持96.9%准确率且零错误。同一数据流也揭示了失败模式：宽松保护会无声地错误标记48.9%的编译结果，而不可靠的退化参考导致验证门禁拒绝重编译。校准精度与参考可信度，而非模型能力，决定低成本是否仍正确。代码见：https://github.com/RightNow-AI/auto
原文摘要 · Abstract (English)
Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded. We present Auto, a compiler that records live agent behavior, measures which parts are secretly deterministic, extracts them into verified programs or distilled specialists, and emits cognition binaries: WebAssembly artifacts whose manifests carry measured guarantees and whose declared capabilities are physically enforced by the sandbox. A tiered runtime executes compiled behavior behind conformally calibrated guards; guard trips deopt to the reference agent, and the captured trace recompiles back down, so nothing is figured out twice. We use "AGI compiler" in one narrow, testable sense: a system that autonomously converts novel experience into permanent, verified, near-free skill while measuring what it does not know. On AUTO-BENCH, a benchmark we introduce and pre-register, 87.1% of 560 recorded frontier-agent spans are witnessed-deterministic (three of the four censused task families measure 100.0%). On a 300-item stream with three scheduled distribution shifts, the closed loop compiles three artifact generations and drives marginal cost from 59 to 2 micro-dollars per item (6.4x end-to-end) at 96.9% parity on witnessed inputs with zero errors. The same stream also quantifies the failure modes: a loose guard silently mislabels 48.9% of compiled answers, and an unfaithful deopt reference causes the verification gate to refuse recompilation. Calibration and reference fidelity, not model capability, decide whether cheap stays correct. Code: https://github.com/RightNow-AI/auto
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。