How to Correctly Do Semantic Backpropagation on Language-based Agentic Systems

Wenyi Wang, Hisham Abdullah Alyahya, Dylan R. Ashley, Oleg Serikov, Dmitrii Khizbullin, Francesco Faccio, Jürgen Schmidhuber

Keywords: Agentic System, Large Language Model, Backpropagation, Computational Graph

TL;DR: We propose semantic backpropagation and semantic gradient descent, generalizations of reverse-mode automatic differentiation, numerical gradient descent, and TextGrad, to solve the Graph-based Agentic System Optimization problem.

Abstract: Language-based agentic systems have shown great promise in recent years, transitioning from solving small-scale research problems to being deployed in challenging real-world tasks. However, optimizing these systems often requires substantial manual labor. Recent studies have demonstrated that these systems can be represented as computational graphs, enabling automatic optimization. Despite these advancements, most current efforts in Graph-based Agentic System Optimization (GASO) fail to properly assign feedback to the system’s components given feedback on the system’s output. To address this challenge, we formalize the concept of semantic backpropagation with semantic gradients—a generalization that aligns several key optimization techniques, including reverse-mode automatic differentiation and the more recent TextGrad by exploiting the relationship among nodes with a common successor. This serves as a method for computing directional information about how changes to each component of an agentic system might improve the system’s output. To use these gradients, we propose a method called semantic gradient descent which enables us to solve GASO effectively. Our results on both BIG-Bench Hard and GSM8K show that our approach outperforms existing state-of-the-art methods for solving GASO problems. A detailed ablation study on the LIAR dataset demonstrates the parsimonious nature of our method.

Primary Area: foundation or frontier models, including LLMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11702