WO2025093936 - GUIDED PROGRAMMING OF AUTONOMOUS AGENTS
National phase entry is expected:
Publication Number
WO/2025/093936
Publication Date
08.05.2025
International Application No.
PCT/IB2024/050480
International Filing Date
18.01.2024
Title **
[English]
GUIDED PROGRAMMING OF AUTONOMOUS AGENTS
[French]
PROGRAMMATION GUIDÉE D'AGENTS AUTONOMES
Applicants **
NEC LABORATORIES EUROPE GMBH
Inventors
FRIEDE, David
SIRACUSANO, Giuseppe
BIFULCO, Roberto
Priority Data
63/546,303
30.10.2023
US
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
EPO
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| 译文 |
|
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing, Examination, Granting | 2039 | |
| EPO | Filing, Examination, Granting | 8741 | |
| Japan | Filing, Examination, Granting | 2214 | |
| South Korea | Filing, Examination, Granting | 2200 | |
| USA | Filing, Examination, Granting | 4740 |
Total:
19,934
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Contact Us
Abstract[English]
In an embodiment, the present invention provides a computer-implemented, machine learning method for guided programming of autonomous agents. A large language model (LLM) prompt is intercepted between an LLM autonomous agent and an LLM. A guiding prompt is selected from a plurality of guiding prompts to inject into the LLM prompt based on a context of the LLM prompt. A modified LLM prompt that includes the selected guiding prompt is sent to the LLM. The modified LLM prompt and answer generated by the LLM is forwarded to the LLM autonomous agent. The method has applications including, but not limited to, use cases in medicine / healthcare, Cyber Threat Intelligence and performance portability of computer code, to optimize processes or predictions or to support decision making.[French]
Dans un mode de réalisation, la présente invention concerne un procédé d'apprentissage automatique, mis en œuvre par ordinateur, pour la programmation guidée d'agents autonomes. Une invite de grand modèle de langage (GML) est interceptée entre un agent autonome GML et un GML. Une invite de guidage est sélectionnée parmi une pluralité d'invites de guidage à injecter dans l'invite GML en fonction d'un contexte de l'invite GML. Une invite GML modifiée qui comprend l'invite de guidage sélectionnée est envoyée au GML. L'invite GML modifiée et la réponse générée par le GML sont transmises à l'agent autonome GML. Le procédé comprend des applications comportant notamment, mais pas exclusivement, des cas d'utilisation dans la médecine / les soins de santé, le renseignement sur les cybermenaces et la portabilité des performances de codes informatiques, pour optimiser des processus ou des prédictions ou pour soutenir la prise de décision.