Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering

TL;DR

This paper introduces Neural Collaborative Context Engineering (NCCE), a novel framework that personalizes context strategies for large language models by recommending optimal contexts for individual inputs, significantly enhancing performance.

Contribution

It reformulates context engineering as a recommendation problem, enabling dynamic, instance-specific context routing rather than a static global search approach.

Findings

NCCE outperforms traditional methods in task accuracy.

Instance-wise context recommendation improves LLM performance.

The framework demonstrates significant gains across multiple tasks.

Abstract

Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly treat this as a global search problem, seeking a single context strategy that maximizes average performance across a dataset. This restrictive assumption overlooks the fact that different inputs often require distinct guidance, leaving substantial instance-level performance gains untapped. In this paper, we propose a paradigm shift by formulating context engineering as a recommendation problem. We introduce \textbf{Neural Collaborative Context Engineering (NCCE)}, a framework that transitions optimization from a static global search to dynamic, instance-wise routing. NCCE first bootstraps a diverse catalog of anchor contexts and then employs a novel \textbf{Context-CF Co-Evolution} mechanism. This stage establishes a synergistic feedback loop: a lightweight Neural Collaborative Filtering (NCF) model learns instance-context preferences to guide the generation of specialized context variants, while the newly evaluated contexts continuously refine the NCF model's understanding of latent preferences. At inference time, the trained NCF model acts as a context router, dynamically assigning the most suitable context strategy to each unseen instance. Theoretical Proofs and comprehensive experiments demonstrate that by matching individual inputs with their optimal contexts, NCCE significantly improves task accuracy, highlighting the critical importance of personalization in LLM context engineering.