Optimizing generative AI by backpropagating language model feedback

Mert Yuksekgonul (), Federico Bianchi, Joseph Boen, Sheng Liu, Pan Lu, Zhi Huang, Carlos Guestrin and James Zou ()
Additional contact information
Mert Yuksekgonul: Stanford University
Federico Bianchi: Stanford University
Joseph Boen: Stanford University
Sheng Liu: Stanford University
Pan Lu: Stanford University
Zhi Huang: Stanford University
Carlos Guestrin: Stanford University
James Zou: Stanford University

Nature, 2025, vol. 639, issue 8055, 609-616

Abstract: Abstract Recent breakthroughs in artificial intelligence (AI) are increasingly driven by systems orchestrating multiple large language models (LLMs) and other specialized tools, such as search engines and simulators. So far, these systems are primarily handcrafted by domain experts and tweaked through heuristics rather than being automatically optimized, presenting a substantial challenge to accelerating progress. The development of artificial neural networks faced a similar challenge until backpropagation and automatic differentiation transformed the field by making optimization turnkey. Analogously, here we introduce TextGrad, a versatile framework that performs optimization by backpropagating LLM-generated feedback to improve AI systems. By leveraging natural language feedback to critique and suggest improvements to any part of a system—from prompts to outputs such as molecules or treatment plans—TextGrad enables the automatic optimization of generative AI systems across diverse tasks. We demonstrate TextGrad’s generality and effectiveness through studies in solving PhD-level science problems, optimizing plans for radiotherapy treatments, designing molecules with specific properties, coding, and optimizing agentic systems. TextGrad empowers scientists and engineers to easily develop impactful generative AI systems.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41586-025-08661-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:639:y:2025:i:8055:d:10.1038_s41586-025-08661-4

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-025-08661-4

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().