Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.16113 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912911290531840 |
|---|---|
| author | Sun, Qi Nielsen, Stefan Yokota, Rio Tang, Yujin |
| author_facet | Sun, Qi Nielsen, Stefan Yokota, Rio Tang, Yujin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16113 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evolutionary Context Search for Automated Skill Acquisition Sun, Qi Nielsen, Stefan Yokota, Rio Tang, Yujin Neural and Evolutionary Computing Machine Learning 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. |
| title | Evolutionary Context Search for Automated Skill Acquisition |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2602.16113 |