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

• URL: http://arxiv.org/abs/2602.08306v1
• Date: Mon, 09 Feb 2026 06:29:32 GMT
• Title: TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
• Abstract summary: TextResNet is a framework that reformulates the optimization process to achieve precise signal routing via four key innovations.<n>Our results show that TextResNet achieves superior performance compared to Text, but also exhibits remarkable stability for agentic tasks in compound AI systems.
• Score: 48.34766553598802
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization [41.70456027589437]
  Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints.<n>We study this failure mode as prompt distributional overfitting and argue that it reflects a lack of representation control in discrete text-space optimization.<n>We propose TextReg, a regularization framework that realizes a soft-penalty objective through regularized textual gradients.
  arXiv  Detail & Related papers  (2026-05-20T15:47:26Z)
• PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution [51.96078493242164]
  PRISM is a single-step diffusion-based Text-SR framework.<n> PRISM achieves state-of-the-art performance with millisecond-level inference.
  arXiv  Detail & Related papers  (2026-05-13T05:31:06Z)
• Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining [59.2578488860426]
  Heterogeneous multi-modal remote sensing object detection aims to accurately detect objects from diverse sensors.<n>Existing approaches largely adopt a late alignment paradigm, in which modality alignment and task-specific optimization are entangled during downstream fine-tuning.<n>We propose BabelRS, a unified language-pivoted pretraining framework that explicitly decouples modality alignment from downstream task learning.
  arXiv  Detail & Related papers  (2026-03-02T11:38:12Z)
• Textual Equilibrium Propagation for Deep Compound AI Systems [63.266386654809544]
  Large language models (LLMs) are increasingly deployed as part of compound AI systems.<n>Recent approaches that propagate textual feedback globally (e.g., TextGrad) make it feasible to optimize such pipelines, but we find that performance degrades as system depth grows.<n>In particular, long-horizon agentic exhibit two depth-scaling failure modes: 1) exploding textual gradient, where textual feedback grows exponentially with depth, leading to prohibitively long message and amplifies evaluation biases; and 2) vanishing textual gradient, where limited long-context ability causes models overemphasize partial feedback and compression of lengthy feedback causes downstream messages to lose specificity gradually
  arXiv  Detail & Related papers  (2026-01-28T21:41:11Z)
• Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration [52.82397287366076]
  All-in-one image restoration aims to handle diverse degradations (e.g., noise, blur, adverse weather) within a unified framework.<n>In this work, we reveal a critical insight: well-crafted feature extraction inherently encodes degradation-carrying information.<n>Our symmetric design preserves intrinsic degradation signals robustly, rendering simple additive fusion in skip connections.
  arXiv  Detail & Related papers  (2025-12-11T12:20:31Z)
• SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation [16.707429579441435]
  SOCIA-Nabla is an end-to-end, agentic framework that treats simulator construction asinstance optimization over code within a textual graph.<n>Specialized computation-driven agents are embedded as graph nodes, and a workflow manager executes a loss-driven loop: code synthesis -> execution -> evaluation -> code repair.
  arXiv  Detail & Related papers  (2025-10-21T12:00:00Z)
• Towards Continual Expansion of Data Coverage: Automatic Text-guided Edge-case Synthesis [1.0152838128195467]
  We propose an automated pipeline for text-guided edge-case synthesis.<n>Our approach employs a Large Language Model, fine-tuned via preference learning, to rephrase image captions.<n>This work establishes a scalable framework that shifts data curation from manual effort to automated, targeted synthesis.
  arXiv  Detail & Related papers  (2025-09-30T12:11:25Z)
• Text2Grad: Reinforcement Learning from Natural Language Feedback [32.59003667154527]
  We introduce Text2Grad, a-grained reinforcement paradigm that turns free-form textual feedback into span-level gradients.<n>Our results demonstrate that natural-language feedback, when converted to gradients, is a powerful signal for finegrained policy optimization.
  arXiv  Detail & Related papers  (2025-05-28T13:23:49Z)
• TextGrad: Automatic "Differentiation" via Text [32.94896315864364]
  TextGrad backpropagates textual feedback to improve individual components of a compound AI system. It works out-of-the-box for a variety of tasks, where the users only provide the objective function without tuning components or prompts of the framework. We showcase TextGrad's effectiveness and generality across a diverse range of applications, from question answering and molecule optimization to radiotherapy treatment planning.
  arXiv  Detail & Related papers  (2024-06-11T17:32:21Z)
• Adaptive Recursive Circle Framework for Fine-grained Action Recognition [95.51097674917851]
  How to model fine-grained spatial-temporal dynamics in videos has been a challenging problem for action recognition. Most existing methods generate features of a layer in a pure feedforward manner. We propose an Adaptive Recursive Circle framework, a fine-grained decorator for pure feedforward layers.
  arXiv  Detail & Related papers  (2021-07-25T14:24:29Z)
• GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training [59.160154997555956]
  We present GradInit, an automated and architecture method for initializing neural networks. It is based on a simple agnostic; the variance of each network layer is adjusted so that a single step of SGD or Adam results in the smallest possible loss value. It also enables training the original Post-LN Transformer for machine translation without learning rate warmup.
  arXiv  Detail & Related papers  (2021-02-16T11:45:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.