机器可解释信息：将文档编译为可搜索且可读的协议状态
Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States
浏览论文内容
中文总结 AI 辅助
提出MII协议，通过双时间尺度Writer将文档编译为固定带宽状态，实现跨模型可转移的检索、推理与重建，Residual-MII在HotpotQA上以7%计算成本超越全上下文精确匹配。
中文摘要 AI 辅助
长上下文语言模型通过原始自然语言与外部知识交互。在检索增强系统中，这造成了持续的索引-载荷分裂：密集向量实现了可搜索的路由，但模型必须重新读取冗长的文本载荷以进行推理，代价是O(N^2)的注意力计算。现有压缩方法进一步产生了与特定架构绑定的私有状态。我们引入了机器可解释信息（MII），这是首个智能体到智能体（A2A）的文档到状态协议。一个双时间尺度的状态空间Writer将文档编译为规范的、固定带宽的状态（56个token），而一个轻量级Translator将其映射到任何冻结的Reader的嵌入空间，将查询时成本降低到O(K)。生成的.mii工件在单一可转移介质中统一了检索（可搜索的几何结构）、推理（全局记忆）和重建（基于事实的细节）。我们展示了跨异构LLM（如Llama、Qwen、Mistral）的强跨模型互操作性——尽管Writer使用旧版GPT-2词汇表，迫使进行真正的语义翻译而非token级记忆。机制探针揭示了模块化的潜在结构：实体表示可以被因果追踪，并在不相关的文档状态之间零样本移植，同时保持可解码性。为了解决固定带宽下的词汇重建问题，我们提出了Residual-MII，一种结合编译全局记忆与稀疏局部证据的缓存层次结构。在HotpotQA（7,405个查询）上，Residual-MII在约7%的注意力FLOPs下超过了全上下文精确匹配，表明向编译的、可转移的神经文档格式的范式转变。
英文摘要
Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent index-payload schism: dense vectors enable searchable routing, but models must re-ingest lengthy text payloads for reasoning at O(N^2) attention cost. Existing compression methods further produce private states tied to specific architectures. We introduce Machine-Interpretable Information (MII), the first agent-to-agent (A2A) document-to-state protocol. A dual-timescale state-space Writer compiles documents into a canonical, fixed-bandwidth state (56 tokens), and a lightweight Translator maps it into any frozen Reader's embedding space, reducing query-time cost to O(K). The resulting .mii artifact unifies Retrieval (searchable geometry), Reasoning (global memory), and Reconstruction (grounded details) in a single transferable medium. We demonstrate strong cross-model interoperability across heterogeneous LLMs (e.g., Llama, Qwen, Mistral) -- despite the Writer using a legacy GPT-2 vocabulary, forcing genuine semantic translation rather than token-level memorization. Mechanistic probes reveal modular latent structure: entity representations can be causally traced and zero-shot transplanted between unrelated document states while remaining decodable. To address lexical reconstruction under fixed bandwidth, we propose Residual-MII, a cache hierarchy combining compiled global memory with sparse local evidence. On HotpotQA (7,405 queries), Residual-MII exceeds full-context Exact Match at approximately 7% of the attention FLOPs, suggesting a paradigm shift toward compiled, transferable neural document formats.
发表机构
- NexusLumenLabs
- Fudan University（复旦大学）
机构由 AI 辅助整理，请以论文原文为准。
