Applications
ADOPT: Adaptive Dependency-Guided Joint Prompt Optimization for Multi-Step LLM Pipelines
arXiv:2512.24933v2 Announce Type: replace-cross Abstract: Multi-step LLM pipelines can solve complex tasks, but jointly optimizing prompts across steps remains challenging due to missing step-level su
arXiv:2512.24933v2 Announce Type: replace-cross Abstract: Multi-step LLM pipelines can solve complex tasks, but jointly optimizing prompts across steps remains challenging due to missing step-level supervision and inter-step dependency. We propose ADOPT, an adaptive dependency-guided joint prompt optimization framework for multi-step LLM pipelines. ADOPT analyzes the dependency between each LLM step and the final output, constructs a global textual gradient from final-task errors, and decomposes it into step-level local textual gradients, providing more precise optimization signals for local prompt updates. It further decouples signal estimation from prompt updating, enabling flexible integration of single-prompt optimizers, and uses a Shapley-based strategy to adaptively allocate optimization resources to high-impact steps. Experiments on real-world datasets and structurally diverse pipelines demonstrate that ADOPT is effective and robust, consistently outperforming strong prompt optimization baselines.
Related
- Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
- Large Language Models for Outpatient Referral: Problem Definition, Benchmarking and Challenges
- Luwen Technical Report
- PIArena: A Platform for Prompt Injection Evaluation
Source: arXiv cs.LG | 2026-04-10