Metraipolis › archive › dc_923296ac366d
Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States — arXiv:2609.23371
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23371
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:48.891Z
- SHA-256 of the archived text
b08d46859ecc29f5b44043056a72d6e9874b912da7e9cfa327965267d2d8c41e- Stable URL of this page
https://metraipolis.com/documento/dc_923296ac366d
How to cite
Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States — arXiv:2609.23371 — arXiv (en), https://arxiv.org/abs/2609.23371 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_923296ac366d (Metraipolis archive dc_923296ac366d, sha256 b08d46859ecc29f5b44043056a72d6e9874b912da7e9cfa327965267d2d8c41e)
BibTeX
@misc{dc923296ac366d,
title = {Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States — arXiv:2609.23371},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23371},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_923296ac366d; sha256 b08d46859ecc29f5b44043056a72d6e9874b912da7e9cfa327965267d2d8c41e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23371. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.23371 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:48:44.988Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).