Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
ACE: Self-Improving LLM Agents
A walkthrough of Agentic Context Engineering, showing how Generator, Reflector, and Curator iteratively refine context to counter brevity bias and boost LLM performance without retraining.
In this talk, I’ll present a practical walkthrough of Agentic Context Engineering (ACE) — a novel framework introduced in the paper “Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models.” I will explain how ACE addresses challenges like brevity bias and context collapse by enabling agents to iteratively refine their own contextual understanding through three core components: the Generator, Reflector, and Curator. Using a simplified case study, I’ll demonstrate how a language-model-based agent can evolve its behavior and improve performance over time without parameter updates, simply by re-engineering its context and memory representations.