Writings and projects

Pasquale Casciano

HOME
CATEGORIES
TAGS
ARCHIVES
ABOUT

Home Categories Reinforcement Learning

Category

Reinforcement Learning 1

Alignment con KTO Nov 3, 2025

Recently Updated

Goal–Plan–Action (GPA) di un sistema multi-agent
Misurazione delle performance del Data Agent
Struttura di agenti e sub-agenti con LangGraph
Agentic Memory: consolidamento della memoria e gestione della context window
Agentic Memory: l'agente memory-aware

Trending Tags

Machine Learning Agentic Memory AI AWS LangChain Memory Manager pgvector PostgreSQL Context Engineering Embedding

© 2026 Pasquale Casciano. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

Machine Learning Agentic Memory AI AWS LangChain Memory Manager pgvector PostgreSQL Context Engineering Embedding

New content available