PLAN-AND-ACT: Improving Planning of Agents for Long-Horizon Tasks

Hong-Wei Wu published on 2025-05-11 included in category Paper Introduction

Explore the PLAN-AND-ACT paper: Learn how its innovative Planner-Executor framework and data synthesis methods enhance Large Language Model (LLM) capabilities in long-horizon task planning and execution, and overcome related challenges.

Intorduction to LangMem

Hong-Wei Wu published on 2025-05-06 included in category Other Topics

Explore the core concepts of Agent Memory (Semantic, Episodic, Procedural) for LLMs. Learn practical implementation of long-term agent memory using LangGraph & LangMem, based on DeepLearning.AI course notes, with a detailed Email Agent example.

HuatuoGPT-o1: Towards Medical Complex Reasoning with LLMs

Hong-Wei Wu published on 2025-01-31 included in category Paper Introduction

Understand how to train an o1-like model on specific domain

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Hong-Wei Wu published on 2025-01-27 included in category Paper Introduction

Dive into the HuggingGPT paper, a key work on LLM Agents. Discover how an LLM acts as a controller for task planning and tool usage to solve multi-modal and complex AI challenges.

EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records

Hong-Wei Wu published on 2025-01-26 included in category Paper Introduction

LLM Agent for Multi-Table QA Task

RAFT: Adapting Language Model to Domain Specific RAG

Hong-Wei Wu published on 2024-10-31 included in category Paper Introduction

RAFT paper analysis: Learn how to train LLMs for Domain-Specific RAG, combining external documents with internal knowledge to boost specialized domain QA performance.

REPLUG: Retrieval-Augmented Black-Box Language Models

Hong-Wei Wu published on 2024-10-31 included in category Paper Introduction

Explore how Retrieval-Augmented Generation (RAG) enhances black-box LLMs. This article details the NAACL 2024 paper REPLUG, discussing its innovative methods for Inference and Training stages to improve LLM answer quality and effectively reduce hallucination.