SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2504.04785 · 2025

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Efficiently leveraging of the capabilities of contemporary large language models (LLMs) is increasingly challenging, particularly when direct fine-tuning is expensive and often impractical. Existing training-free methods, including manually or automated designed workflows, typically demand substantial human effort or yield suboptimal results. This paper proposes Weak-for-Strong Harnessing (W4S), a novel framework that customizes smaller, cost-efficient language models to design and optimize workflows for harnessing stronger models. W4S formulates workflow design as a multi-turn markov decision process and introduces reinforcement learning for agentic workflow optimization (RLAO) to train a weak meta-agent. Through iterative interaction with the environment, the meta-agent learns to design increasingly effective workflows without manual intervention. Empirical results demonstrate the superiority of W4S that our 7B meta-agent, trained with just one GPU hour, outperforms the strongest baseline by 2.9% ~ 24.6% across eleven benchmarks, successfully elevating the performance of state-of-the-art models such as GPT-3.5-Turbo and GPT-4o. Notably, W4S exhibits strong generalization capabilities across both seen and unseen tasks, offering an efficient, high-performing alternative to directly fine-tuning strong models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2504.04785")
get_code_for_paper("2504.04785")
have("2504.04785")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2504.04785.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2504.04785.svg)](https://syntology.ai/paper/2504.04785)

Connect an agent — have() is free.