ZERA: Zero-init Instruction Evolving Refinement Agent -- From Zero Instructions to Structured Prompts via Principle-based Optimization
This addresses the need for more efficient and robust prompt optimization methods in AI, though it appears incremental as it builds on prior APO work with a novel refinement approach.
The paper tackles the problem of automatic prompt optimization for large language models by proposing ZERA, a framework that jointly optimizes system and user prompts using structured, principle-based critiques, achieving consistent improvements across five LLMs and nine diverse datasets.
Automatic Prompt Optimization (APO) improves large language model (LLM) performance by refining prompts for specific tasks. However, prior APO methods typically focus only on user prompts, rely on unstructured feedback, and require large sample sizes and long iteration cycles-making them costly and brittle. We propose ZERA (Zero-init Instruction Evolving Refinement Agent), a novel framework that jointly optimizes both system and user prompts through principled, low-overhead refinement. ZERA scores prompts using eight generalizable criteria with automatically inferred weights, and revises prompts based on these structured critiques. This enables fast convergence to high-quality prompts using minimal examples and short iteration cycles. We evaluate ZERA across five LLMs and nine diverse datasets spanning reasoning, summarization, and code generation tasks. Experimental results demonstrate consistent improvements over strong baselines. Further ablation studies highlight the contribution of each component to more effective prompt construction. Our implementation including all prompts is publicly available at https://github.com/younatics/zera-agent.