Large Language Models (LLMs) demonstrate remarkable capabilities, yet their inability to maintain persistent memory in long contexts limits their effectiveness as autonomous agents in long-term interactions. While existing memory systems have made progress, their reliance on arbitrary granularity for defining the basic memory unit and passive, rule-based mechanisms for knowledge extraction limits their capacity for genuine learning and evolution. To address these foundational limitations, we present Nemori, a novel self-organizing memory architecture inspired by human cognitive principles. Nemori's core innovation is twofold: First, its Two-Step Alignment Principle, inspired by Event Segmentation Theory, provides a principled, top-down method for autonomously organizing the raw conversational stream into semantically coherent episodes, solving the critical issue of memory granularity. Second, its Predict-Calibrate Principle, inspired by the Free-energy Principle, enables the agent to proactively learn from prediction gaps, moving beyond pre-defined heuristics to achieve adaptive knowledge evolution. This offers a viable path toward handling the long-term, dynamic workflows of autonomous agents. Extensive experiments on the LoCoMo and LongMemEval benchmarks demonstrate that Nemori significantly outperforms prior state-of-the-art systems, with its advantage being particularly pronounced in longer contexts.
This tutorial demonstrates how to perform document clustering using LLM embeddings with scikit-learn. It covers generating embeddings with Sentence Transformers, reducing dimensionality with PCA, and applying KMeans clustering to group similar documents.
A curated reading list for those starting to learn about Large Language Models (LLMs), covering foundational concepts, practical applications, and future trends, updated for 2026.
This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.
This article details research into finding the optimal architecture for small language models (70M parameters), exploring depth-width tradeoffs, comparing different architectures, and introducing Dhara-70M, a diffusion model offering 3.8x faster throughput with improved factuality.
This article explores different chunking strategies for Retrieval-Augmented Generation (RAG) systems, comparing nine approaches using the agenticmemory library to improve retrieval accuracy and reduce hallucinations.
A recent study shows that one large language model (LLM) demonstrates impressive linguistic analysis abilities, rivaling those of human linguistics graduate students. Researchers tested LLMs on complex linguistic tasks, including recursion and phonological rule inference, revealing that OpenAI’s o1 model performed significantly better than others, challenging conventional views on the limits of AI in understanding language.
This article details the process of building a fast vector search system for a large legal dataset (Australian High Court decisions). It covers choosing embedding providers, performance benchmarks, using USearch and Isaacus embeddings, and the importance of API terms of service. It focuses on achieving speed and scalability while maintaining reasonable accuracy.
An extremely lightweight universal grammar implementation with provable recursion, based on Chomsky's Minimalist Grammar theory, fitting in under 50kB with zero runtime dependencies. It includes a probabilistic language model extension and formal verification.
This page details the command-line utility for the Embedding Atlas, a tool for exploring large text datasets with metadata. It covers installation, data loading (local and Hugging Face), visualization of embeddings using SentenceTransformers and UMAP, and usage instructions with available options.
