https://x.com/_philschmid/status/1977618096383721725

Is ACE the next Context Engineering Technique? ACE (Agentic Context Engineering) is a new framework that beats current state-of-the-art optimizers like GEPA by treating context as an evolving, structured space of accumulated knowledge.

ACE会是下一代情境工程技术吗？ACE（Agentic Context Engineering，自主情境工程）作为一种新型框架，通过将情境视为一个不断进化的结构化知识累积空间，其表现超越了当前最先进的优化器（如GEPA）。

What is ACE?

ACE treats context as an evolving space rather than a static prompt. Instead of rewriting the entire context it manages it as a collection of discrete, structured items (strategies, code snippets, error handlers) that are incrementally accumulated, refined, and organized over time based on performance feedback.

ACE将上下文视为一个动态演化的空间，而非静态提示。它不会重写整个上下文，而是将其管理为离散化、结构化的元素集合（策略、代码片段、错误处理器），这些元素会随着时间推移，根据性能反馈逐步积累、优化和组织。

ACE vs. GEPA (Current SOTA)

GEPA (Genetic-Pareto) is a popular method that uses evolutionary algorithms to iteratively rewrite and optimize prompts for brevity and general performance, but it can suffer from "brevity bias" and "context collapse", erasing specific, detailed heuristics needed for complex domain tasks. ACE builds a comprehensive context. It prioritizes retaining detailed domain insights and uses non-LLM logic to manage context growth, ensuring that hard-learned constraints and edge-case strategies are preserved rather than summarized away. How it works:

GEPA（遗传帕累托）是一种流行方法，它利用进化算法迭代重写并优化提示词以实现简洁性和通用性能，但可能陷入"简洁性偏差"和"上下文坍塌"问题，抹除复杂领域任务所需的特定细节启发式规则。而ACE构建的是全面上下文框架，优先保留专业领域洞察细节，并采用非大语言模型逻辑来管理上下文扩展，确保通过艰难实践获得的约束条件和边缘案例策略得以保留而非被概括性处理。其运作原理如下：

Three components: a Generator (to solve tasks), a Reflector (to analyze outcomes), and a Curator (to manage the context).

The Generator attempts a task using the current context, creates a reasoning trajectory and environment feedback (e.g., code execution results).

The Reflector provides feedback to extract concrete insights, identifying successful tactics or root causes of errors.

The Curator synthesizes these into structured, itemized "delta" entries (specific additions or edits to knowledge bullets).

Programmatically merge these delta updates into the context, ensuring the context grows and refines incrementally for the next task. Insights:

 GEPA optimize for concise prompts, ACE prioritizes comprehensive, detailed context.

 ACE outperformed baselines by +10.6% on agentic benchmarks and +8.6% on complex financial reasoning.

 ACE's incremental "delta" update approach reduced adaptation latency by an average of 86.9% compared to methods that rewrite full prompts.

 Generator, Reflector and Curator Prompts are part of the paper appendix.

论文

https://www.marktechpost.com/2025/10/10/agentic-context-engineering-ace-self-improving-llms-via-evolving-contexts-not-fine-tuning/

Agentic Context Engineering (ACE): Self-Improving LLMs via Evolving Contexts, Not Fine-Tuning

By

 Asif Razzaq

 -

October 10, 2025

TL;DR: A team of researchers from Stanford University, SambaNova Systems and UC Berkeley introduce ACE framework that improves LLM performance by editing and growing the input context instead of updating model weights. Context is treated as a living “playbook” maintained by three roles—Generator, Reflector, Curator—with small delta items merged incrementally to avoid brevity bias and context collapse. Reported gains: +10.6% on AppWorld agent tasks, +8.6% on finance reasoning, and ~86.9% average latency reduction vs strong context-adaptation baselines. On the AppWorld leaderboard snapshot (Sept 20, 2025), ReAct+ACE (59.4%) ≈ IBM CUGA (60.3%, GPT-4.1) while using DeepSeek-V3.1.

https://arxiv.org/html/2510.04618v1