Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Understand

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates.

• Prior approaches improve usability but often suffer from brevity bias, which drops domain insights for concise summaries, and from context collapse, where iterative rewriting erodes details over time.
• We introduce ACE (Agentic Context Engineering), a framework that treats contexts as evolving playbooks that accumulate, refine, and organize strategies through a modular process of generation, reflection, and curation.
• ACE prevents collapse with structured, incremental updates that preserve detailed knowledge and scale with long-context models.