Skip to content
#generative ai Open access

Диалогическая когнитивная система с внешне сохраняемым состоянием: новая архитектура совместного мышления человека и ИИ

Oct 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

В статье предлагается концепция диалогической когнитивной системы с внешне сохраняемым состоянием как особой архитектуры совместного мышления человека и генеративного искусственного интеллекта. Рассматривается ситуация, в которой развивающееся рассуждение сохраняется во внешнем диалоге и может продолжаться после временного перерыва без восстановления процесса с нуля. Показано, что сохраняется не только информация, но и структура текущего рассуждения: гипотезы, аргументы, возражения, связи, промежуточные решения и нерешённые вопросы. Генеративный ИИ в такой системе выступает не только как инструмент получения или обработки информации, но и как участник последующего преобразования сохранённого состояния. Предлагаемая концепция связывается с исследованиями расширенной и распределённой когниции, когнитивного offloading, транзактивной памяти и совместного творчества человека и ИИ. Формулируются основные элементы архитектуры и направления её дальнейшего эмпирического исследования.* * *The article proposes the concept of a dialogical cognitive system with an externally persistent state as a distinct architecture of joint thinking between humans and generative artificial intelligence. It examines situations in which an evolving reasoning process is preserved in an external dialogue and can be resumed after a temporal interruption without reconstructing the process from the beginning. The preserved state includes not only information, but also hypotheses, arguments, objections, connections, intermediate conclusions, and unresolved questions. Within such a system, generative AI functions not merely as a tool for obtaining or processing information, but also as a participant in the subsequent transformation of the preserved state of reasoning. The concept is related to research on extended and distributed cognition, cognitive offloading, transactive memory, and human–AI co-creativity. The article defines the principal elements of the proposed architecture and outlines directions for its further empirical investigation.

View source

Similar papers

#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations

Related blog posts

Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.