TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning

TL;DR

TextResNet introduces a novel framework for optimizing compound AI systems by decoupling and routing feedback signals, significantly improving stability and performance in deep AI workflows.

Contribution

It presents four key innovations—Semantic Deltas, Gradient Decomposition, Causal Routing, and Density Scheduling—that enhance gradient flow and signal clarity in complex AI systems.

Findings

Outperforms TextGrad in accuracy and stability

Achieves better gradient disentanglement in deep chains

Demonstrates robustness in agentic tasks

Abstract

Textual Gradient-style optimizers (TextGrad) enable gradient-like feedback propagation through compound AI systems. However, they do not work well for deep chains. The root cause of this limitation stems from the Semantic Entanglement problem in these extended workflows. In standard textual backpropagation, feedback signals mix local critiques with upstream contexts, leading to Attribution Ambiguity. To address this challenge, we propose TextResNet, a framework that reformulates the optimization process to achieve precise signal routing via four key innovations. Firstly, in the forward pass, it enforces Additive Semantic Deltas to preserve an Identity Highway for gradient flow. Secondly, in the backward pass, it introduces Semantic Gradient Decomposition via a Semantic Projector to disentangle feedback into causally independent subspaces. Thirdly, it implements Causal Routing, which routes projected signals to their specific components. Finally, it performs Density-Aware Optimization Scheduling to leverage the disentangled signals to dynamically allocate resources to key system bottlenecks. Our results show that TextResNet not only achieves superior performance compared to TextGrad, but also exhibits remarkable stability for agentic tasks in compound AI systems where baselines collapse. Code is available at https://github.com/JeanDiable/TextResNet.