LATIDIA · Ciberseguridad

Janus: Sagas de evidencia antes del efecto y procedencia verificable fuera de línea para LLM genéticos

arXiv: 2609.38266v1Tipo de anuncio: nuevo Resumen: Los modelos genéticos de lenguaje grande (LLM) ahora mueven dinero a través de herramientas, sin embargo, el registro de lo que hicieron suele ser un rastro que su propio proceso emite al lado del efecto. Janus pone

La noticia

arXiv:2609.38266v1 Announce Type: new Abstract: Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside the effect. Janus puts the record on the effect path. A step's proposal, the verdict on it and any answer from a validator or a person are durable in a signed, hash-chained log before the step may run or its effect be released; with keys declared, each answer is signed by whoever gave or relayed it. Gates are pure functions of that log, and an auditor re-derives every verdict offline from the log and one public key. At the