Новости

26.01.2024 г. прошло заседание международного онлайн-семинара «Искусственные общества и информационные технологии», посвященное докладу Yule Wang (PhD, MLE/GenAI Engineer at Mission Cloud Consulting Simon Fraser University, Ontario, Canada).

Тема доклада: Self-improve LLM-based Agent and its Prospects

Краткая аннотация:
Large Language Models (LLMs) like GPT-4 have revolutionized user-computer interaction through their intuitive natural language interfaces, adeptly handling complex problems. They excel in deconstructing intricate problems into manageable segments, providing step-by-step solutions, actions and evaluations. Such capabilities position them as versatile tools for a range of challenges. Despite their strengths, LLMs face limitations due to their closed-system nature, particularly in accessing up-to-date information and specialized knowledge. This can lead to inaccuracies or "hallucinations" – generating false information. Customizing these models through fine-tuning might seem a solution, but it narrows their generality. This process requires fine-tuning the neural network parameters and datasets for each specific domain, which doesn't fully address challenges like performing arithmetic and staying current with the latest information. These gaps highlight the need for integrating external data sources and additional functionalities into LLMs. Reflecting on historical AI concepts like Minsky's "Society of Minds" from the 1980s and Schmidhuber's "Learning to Think" from the 1990s, we ponder whether current LLM-agent systems are advancing towards these visionary ideas and the ultimate goal of Artificial General Intelligence (AGI). This presentation explores the evolution of LLM-based agents, from basic models to those resembling human cognitive complexity, providing an engineering perspective on their underlying architecture. It concludes by speculating on the future roles of LLM-based agents in bridging the gap towards realizing the AGI future.

В заседании приняли участие представители России (ЦЭМИ РАН, МГУ, Уфимский научный центр РАН, Воронежский государственный университет), Китайской народной республики (University of Chinese Academy of Sciences, Milestone software company), Великобритании (University of Southampton), Канады (Simon Fraser University), Болгарии (‎American University in Bulgaria) и Казахстана (Евразийский национальный университет им. Л. Н. Гумилева, Нур-Султан).

Заявки на участие в будущих семинарах принимаются по адресу: tatiasha@yandex.ru

Видеозапись семинара

Фото:













Возврат к списку

  • О ЦЭМИ
  • Организационная структура ЦЭМИ
  • Деятельность института
  • Научные исследования
  • Подготовка научных кадров
  • Публикации
  • Диссертационные советы
  • Новости
  • Точка зрения
  • Архив
Последние новости: