用进化算法自动找最优上下文，让大模型不重训也能学会新技能。
Evolutionary Context Search for Automated Skill Acquisition
- 通过进化搜索优化上下文组合，用小样本验证效果。
- 在BackendBench上提升27%，τ-bench航空任务提升7%。
- 结果可跨模型通用，适合不想微调又想提效的开发者。
大语言模型部署后难以可靠获取新知识，即使有相关文本资源，也难以转化为可用知识，除非重新训练。检索增强生成试图在推理时引入相关文档以弥补这一差距，但基于相似性的检索常无法找到真正提升任务表现的上下文。我们提出进化式上下文搜索（ECS），一种无需权重更新、仅需推理调用的进化方法，通过小规模开发集上的准确率来搜索上下文组合。ECS超越语义相似性，发现能显著提升性能的非显式上下文配对。实验表明，ECS使BackendBench性能提升27%，τ-bench航空任务提升7%。所生成的上下文具有模型无关性，用Gemini-3-Flash训练的上下文可有效迁移至Claude Sonnet和DeepSeek。这表明ECS为自动化技能获取开辟了新路径，是替代手动提示工程或高成本微调的高效方案。
原文摘要 · Abstract (English)
Large Language Models cannot reliably acquire new knowledge post-deployment -- even when relevant text resources exist, models fail to transform them into actionable knowledge without retraining. Retrieval-Augmented Generation attempts to bridge this gap by surfacing relevant documents at inference time, yet similarity-based retrieval often fails to identify context that actually improves task performance. We introduce Evolutionary Context Search (ECS), an evolutionary method that searches context combinations using accuracy on a small development set, requiring only inference calls without weight updates. ECS moves beyond semantic similarity to discover non-obvious context pairings that significantly boost performance. Our empirical results show that ECS improves BackendBench by 27\% and $τ$-bench airline by 7\%. The evolved contexts are model-agnostic, as those evolved with Gemini-3-Flash transfer effectively to Claude Sonnet and DeepSeek. This suggests that ECS opens a path toward automated context discovery for skill acquisition -- an efficient alternative to manual prompt engineering or costly fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。