Towards more Contextual Agents: An extractor-Generator Optimization Framework

TL;DR

This paper presents an automated Extractor-Generator framework to optimize prompts for LLM-based agents, significantly improving their performance in context-specific tasks by enhancing adaptability and reducing manual effort.

Contribution

It introduces a novel two-stage optimization framework that automates prompt enhancement for contextual LLM agents, addressing scalability and accuracy issues in specialized domains.

Findings

Framework improves agent performance in context-specific tasks

Automates prompt optimization reducing manual effort

Enhances generalization across diverse inputs

Abstract

Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications. However, their performance often degrades in context-specific scenarios, such as specialized industries or research domains, where the absence of domain-relevant knowledge leads to imprecise or suboptimal outcomes. To address this challenge, our work introduces a systematic approach to enhance the contextual adaptability of LLM-based agents by optimizing their underlying prompts-critical components that govern agent behavior, roles, and interactions. Manually crafting optimized prompts for context-specific tasks is labor-intensive, error-prone, and lacks scalability. In this work, we introduce an Extractor-Generator framework designed to automate the optimization of contextual LLM-based agents. Our method operates through two key stages: (i) feature extraction from a dataset of gold-standard input-output examples, and (ii) prompt generation via a high-level optimization strategy that iteratively identifies underperforming cases and applies self-improvement techniques. This framework substantially improves prompt adaptability by enabling more precise generalization across diverse inputs, particularly in context-specific tasks where maintaining semantic consistency and minimizing error propagation are critical for reliable performance. Although developed with single-stage workflows in mind, the approach naturally extends to multi-stage workflows, offering broad applicability across various agent-based systems. Empirical evaluations demonstrate that our framework significantly enhances the performance of prompt-optimized agents, providing a structured and efficient approach to contextual LLM-based agents.