LangChainJP
@LangChainJP
Followers
7K
Following
406
Media
738
Statuses
2K
LLMアプリケーション開発フレームワークLangChain/LangGraphのアップデートや、LLMアプリケーション開発に関連するニュースを日本語でお届け。
Joined November 2024
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning - arXiv👇.
arxiv.org
Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder...
0
0
0
【Memory-R1：LLMに外部メモリ管理能力を付与する強化学習フレームワーク】. Memory-R1は、Memory ManagerとAnswer Agentの2エージェントからなる強化学習フレームワークである。Memory ManagerがADD/UPDATE/DELETE/NOOP（No Operation）の操作を学習し、Answer
1
0
3
Build an AI Agent with LangGraph - Atomic Object’s blog👇.
spin.atomicobject.com
At a recent event, I teamed up with a co-worker to build a simple AI-powered news aggregation agent using LangGraph.
0
0
0
【LangGraphを用いたAIニュース集約エージェントの実装】. LangGraphを用いてニュース集約エージェントを構築する手法を紹介。エージェントは入力に応じて3モード（日次ブリーフィング、トリビア、単一ソース要約）を自動選択し、Tavily
1
0
21
[2508.15884] Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search - arXiv👇.
arxiv.org
We present Jet-Nemotron, a new family of hybrid-architecture language models, which matches or exceeds the accuracy of leading full-attention models while significantly improving generation...
0
0
0
Agentic Knowledge Graph Construction - �.
deeplearning.ai
Build a multi-agent system that plans, designs, and constructs a knowledge graph.
0
0
3
【マルチエージェントシステムによるナレッジグラフ自動構築コースが公開】. 、Neo4jと協力し、Agentic Knowledge Graph
1
14
132
Detecting and countering misuse of AI: August 2025 \ Anthropic👇.
anthropic.com
Anthropic's threat intelligence report on AI cybercrime and other abuses
0
1
2
【AnthropicがAI悪用に関する脅威情報レポートを発表】. Anthropicは、Threat Intelligence Report: August 2025を発表した。報告はAgentic AIが助言にとどまらず攻撃実行にも使われた事例を示し、Claude
1
4
15
[2508.18929] Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework - arXiv👇.
arxiv.org
Retrieval-augmented generation (RAG) systems improve large language model outputs by incorporating external knowledge, enabling more informed and context-aware responses. However, the...
0
0
1
The Responses API in Azure AI Foundry is now generally available | Microsoft Community Hub👇.
techcommunity.microsoft.com
We’re excited to announce the general availability of the Responses API in Azure AI Foundry, making it easier than ever for developers to build intelligent,...
0
0
0
【Azure AI FoundryのResponses APIが一般提供開始】. MicrosoftがAzure AI FoundryのResponses APIの一般提供を開始した。単一APIでエージェント開発を簡素化し、マルチターンの状態管理とツール呼び出しを備える。File
1
2
15
Coral-Protocol/Anemoi: Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol - GitHub👇.
github.com
Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol - Coral-Protocol/Anemoi
0
0
0
Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral Protocol - arXiv👇.
arxiv.org
Recent advances in generalist multi-agent systems (MAS) have largely followed a context-engineering plus centralized paradigm, where a planner agent coordinates multiple worker agents through...
1
1
1
【Coral ProtocolがAgent-to-Agent通信を実現するマルチエージェントシステム「Anemoi」を発表】. Coral
1
13
88
VectifyAI/PageIndex: 📄🧠 PageIndex: Document Index for Reasoning-based RAG - GitHub👇.
github.com
📄🧠 PageIndex: Document Index for Reasoning-based RAG - VectifyAI/PageIndex
0
2
16
【ベクトル検索RAGの課題に対応するReasoning-based RAG「PageIndex」公開】. VectifyAIがReasoning-based
2
47
434
Gemini is now available anywhere | Google Cloud Blog👇.
cloud.google.com
With Gemini on GDC, you can now leverage Google AI anywhere, while still controlling your sensitive data.
0
0
0