AI Agent Architecture: From Harness to Self-Evolution

Diagram of AI agent architecture showing the model wrapped by a harness, loops, and self-evolving layers

Let me start with a confession that should worry you slightly. The large language model at the heart of every “AI agent” you’ve read about is, on its own, utterly helpless. It cannot remember what it did five minutes ago, press a button, read a file, run a test, or check whether its own brilliant …

Read more

An In-Depth Look at Group Relative Policy Optimization (GRPO)

In recent months, the DeepSeek team has showcased impressive results by fine-tuning large language models for advanced reasoning tasks using an innovative reinforcement learning technique called Group Relative Policy Optimization (GRPO). In this post, we’ll explore the theoretical background and core principles of GRPO while also offering a primer on Reinforcement Learning (RL) and its …

Read more

Advancing LLM Fine-Tuning with Group Relative Policy Optimization (GRPO)

Reinforcement Learning (RL) has become a powerful technique for fine-tuning large models, especially Large Language Models (LLMs), to improve their performance on complex tasks. One of the latest innovations in this area is Group Relative Policy Optimization (GRPO), a new RL algorithm introduced by the DeepSeek team. GRPO was designed to tackle the challenges of …

Read more