Metraipolis › archive › dc_aaef567d291a
mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers — arXiv:2609.00453
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00453
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:31:52.336Z
- SHA-256 of the archived text
5316b02fbc99dc7fbf31e657db907ddc2bee1e5b827352b7027107324c2ccef4- Stable URL of this page
https://metraipolis.com/documento/dc_aaef567d291a
How to cite
mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers — arXiv:2609.00453 — arXiv (en), https://arxiv.org/abs/2609.00453 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aaef567d291a (Metraipolis archive dc_aaef567d291a, sha256 5316b02fbc99dc7fbf31e657db907ddc2bee1e5b827352b7027107324c2ccef4)
BibTeX
@misc{dcaaef567d291a,
title = {mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers — arXiv:2609.00453},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00453},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aaef567d291a; sha256 5316b02fbc99dc7fbf31e657db907ddc2bee1e5b827352b7027107324c2ccef4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00453. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Giving an agent a file about a named expert can supply hard-to-find material, produce a recognizable persona, or change what the agent decides. These are different claims. We test each one. mimeo is an open-source tool that finds a person's public work, checks each extracted quotation against the cached source text, and writes a file an agent can load. Eight logged builds averaged 38 model calls; the check rejects 13.2% of extracted quotations. We tested four expert files with one coding-agent harness. Knowledge access was clearest: mimeo answered all 20 obscure, quotation-heavy questions; no closed-book condition answered more than 10. Keyword search (BM25) over the same pages answered 15-17, a gap this sample cannot resolve. Grounding showed one clear benefit: personas written from model memory misstated a documented position on 1-4 of 20 answers under every grader; the plain agent and mimeo never did. Every persona was easy to spot on short open prompts, and adding task material lowered identification by 18-23 points. mimeo was no more identifiable than a from-memory profile. Judgment transfer remained unresolved because both tests hit their ceiling: every condition found 94-97% of the problems planted in engineering tasks and scored 94-100% on 16 new application scenarios. An AI-judged "sounds like the expert" score changed with the judge: two of four preferred answers based on a model's stereotype, while two found no difference on the same text. That is a caution against relying on a single AI judge. The evidence supports mimeo as a compact, inspectable reference on a person, not as a demonstrated transfer of their judgment. Toolkit and expert profiles: this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00453 — 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 2026-10-17T06:15:12.603Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).