Large Language Model applications increasingly rely on context adaptation rather than weight updates. Current approaches suffer from two critical limitations:

ACE treats contexts as evolving playbooks that accumulate, refine, and organize strategies through a modular process.

ACE consistently outperforms strong baselines across agent and domain-specific benchmarks:

Matches top-ranked production-level agent on AppWorld leaderboard using smaller open-source model.

ACE achieves significant efficiency improvements compared to existing methods:

Adapts effectively without labeled supervision by leveraging natural execution feedback.

• Enables scalable, efficient, and self-improving LLM systems with low overhead
• Provides interpretable contexts and lower overhead compared to fine-tuning
• Offers a flexible approach for online and continuous learning
• Particularly valuable for specialized domains and long-context applications