February 2025
Intermediate
376 pages
9h 25m
Japanese
Content preview from 仕組みからわかる大規模言語モデル 生成AI時代のソフトウェア開発入門
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Reflexion
3.9
Reflexionは、LLM を用いたエージェントをプロンプトの反復的な改善で性能を改善する
学習手法です。ここで言う学習とは、LLMのパラメータ更新を伴うファインチューニングの
ようなTransformerのパラメータ更新を伴う学習ではありません。LLM自身がタスクを試行
した結果を分析し、言語的なフィードバックを生成することで、自己改善することを指しま
す。言語的なフィードバックを次に試行するときのプロンプトにコンテキストとして組み込む
ため、一種の文脈内学習とも言えます。
Reflexionでは、言語的なフィードバックを経験として長期記憶として保存し、次の試行時
に参照することで、エージェントの性能を向上させます。一方、試行ごとに必要な情報は短期
記憶として保存します。
3.9.1
エージェントの構成
Reflexionにおけるエージェントは、図 3.9.1のようにActor、Evaluator、Self-Reflection
の三つの構成要素を用いて与えられたタスクを実行します。これらの構成要素はそれぞれが
LLMを利用して各々の役割を果たします。推論の際、Actorは短期記憶に格納した軌跡
（Trajectory）と 長期記憶から抽出した重要な経験をコンテキストとしてプロンプトに組み込
みLLM に渡します。ここの軌跡とは、エージェントが過去に行った推論や行動（プロンプト
とLLM の出力）と観測のシーケンスを指します。なお、3.8で紹介したReActの一連のプロ
セスは軌跡に相当します。 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.