Helix: A Dual-Helix Co-Evolutionary Multi-Agent System for Prompt Optimization and Question Reformulation

2026-03-20

AI Summary

This work addresses key limitations in existing automatic prompt optimization methods—namely, their reliance on fixed templates, restricted search spaces, and neglect of the intrinsic coupling between problem formulation and prompt design. To overcome these challenges, we propose Helix, a multi-agent system that treats problem restatement and prompt optimization as a unified, joint task. Helix employs a three-stage co-evolutionary framework: a planner decomposes the objective, a dual-track co-evolution mechanism iteratively refines both problem formulations and prompt instructions, and a strategy-driven generator produces high-quality problem restatements. Evaluated across twelve benchmarks, Helix significantly outperforms six strong baselines, achieving up to a 3.95% improvement in task performance while maintaining efficient optimization capabilities.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Prompt Engineering / Prompting
• Multiagent Systems: Distributed Problem Solving

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Automated prompt optimization (APO) aims to improve large language model performance by refining prompt instructions. However, existing methods are largely constrained by fixed prompt templates, limited search spaces, or single-sided optimization that treats user questions as immutable inputs. In practice, question formulation and prompt design are inherently interdependent: clearer question structures facilitate focused reasoning and task understanding, while effective prompts reveal better ways to organize and restate queries. Ignoring this coupling fundamentally limits the effectiveness and adaptability of current APO approaches. We propose a unified multi-agent system (Helix) that jointly optimizes question reformulation and prompt instructions through a structured three-stage co-evolutionary framework. Helix integrates (1) planner-guided decomposition that breaks optimization into coupled question-prompt objectives, (2) dual-track co-evolution where specialized agents iteratively refine and critique each other to produce complementary improvements, and (3) strategy-driven question generation that instantiates high-quality reformulations for robust inference. Extensive experiments on 12 benchmarks against 6 strong baselines demonstrate the effectiveness of Helix, achieving up to 3.95% performance improvements across tasks with favorable optimization efficiency.

Problem

• prompt optimization
• question reformulation
• co-evolution
• multi-agent system
• large language models

Innovation

• prompt optimization
• question reformulation
• multi-agent system
• co-evolutionary framework
• large language models