Skip to content
AI-generated research idea🟢Easy🔧Minor TweakNo close match found

Universal Prompt Optimization via Multi-Model Adversarial Feedback

Optimize prompts for multiple language models simultaneously using an adversarial minimax objective that maximizes the minimum win-rate across an ensemble.

Time

a few days

Compute level

Single GPU or less

Resources

Access to multiple LLM APIs (OpenAI, Anthropic, local Llama).

Prerequisites

Basic ML knowledge, API integration.

Scope

Modify existing code (parallel execution logic).

The Gap

The 'Limitations' section notes that SPO currently optimizes prompts for a single model. The ablation study (Table 2) shows that prompts optimized on one model (e.g., Claude-3.5) do not always transfer perfectly to others (e.g., Llama-3-70B).

Limitation

The current optimization creates prompts that may exploit specific quirks or 'latent probabilistic biases' of the target model, resulting in brittle prompts that fail when model versions change or when deployed on cheaper, smaller models.

Proposed Solution

Modify the execution function φexe to generate outputs from an ensemble of models (M1, M2, M3) simultaneously. The evaluation function φeval would then aggregate pairwise win-rates across all models. The optimizer φopt would be conditioned to maximize the 'minimum win-rate' across the ensemble, acting as a minimax object to find universally robust prompts.

Why This Matters

This solves the 'model lock-in' problem, creating robust prompts that allow developers to switch backend LLMs (e.g., from GPT-4 to Llama-3) without re-optimizing their entire prompt library.

How to Get Started

  1. Establish an API evaluation harness supporting multiple open and closed-source large language models.
  2. Implement a multi-model execution function that generates parallel outputs for candidate prompts.
  3. Define an aggregation metric focusing on the worst-case win-rate across the ensemble.
  4. Run optimization loops using the multi-model feedback and evaluate cross-model prompt transferability.

Code linked to this paper on Hugging Face: github.com/geekan/metagpt

Suggested by AI. Adapt it to your setup.

Has This Been Done?

No close match in 10 results

Works like Universal and Transferable Adversarial Attacks on Aligned Language Models and Fight Back Against Jailbreaking via Prompt Adversarial Tuning discuss adversarial prompts and robustness. However, none of the listed papers implement a minimax optimization framework using ensemble win-rates across multiple models for universal prompt optimization.

We searched OpenAlex for “Optimize prompts for multiple language models simultaneously using an adversarial minimax objective that maximizes the minimum win-rate across an ensemble.” and “Universal Prompt Optimization via Multi-Model Adversarial Feedback” and an AI compared the idea with the top 10 results. A small search can miss relevant work.

Source Paper

Self-Supervised Prompt Optimization

Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu +6 more · 2025

The paper introduces Self-Supervised Prompt Optimization (SPO), a framework designed to automate the improvement of prompts for Large Language Models (LLMs) without relying on ground truth data or human feedback. SPO leverages the inherent capability of LLMs to distinguish better answers through pairwise comparisons (Output vs. Output) to guide the optimization process, achieving state-of-the-art performance at a fraction of the cost of existing methods.

Related Ideas

Is this a good idea?

Share onXLinkedIn