SOURCE-LINKED INTELLIGENCE

ClusterFewshot: Improving Few-shot Optimization for LLMs workflow

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

The performance of large language model (LLM) workflows often depends on selecting a small set of in-context demonstrations to guide model behavior on new tasks. Recent methods improve this process by augmenting prompts with successful reasoning paths. However, their demonstration selection relies on random sampling or metric-based rankings, overlooking the semantic structure of the task. We propose ClusterFewshot, a strategy that combines semantic structuring with utility-aware scoring to construct representative and effective few-shot demonstration sets. Evaluated within DSPy-based pipelines

Read original source ↗ Open in workspace

recordType

paper

region

Global