Search papers, labs, and topics across Lattice.
The paper introduces Adaptive Prompt Structure Factorization (aPSF), a framework for automated prompt optimization that decomposes monolithic prompts into semantic factors using an Architect model. aPSF then optimizes these factors independently via interventional scoring and error-guided selection, enabling more efficient credit assignment and targeted updates. Experiments on reasoning benchmarks show aPSF achieves up to 2.16% higher accuracy and reduces optimization costs by 45-87% compared to existing methods.
Decomposing prompts into independently optimizable "factors" lets you zero in on failure points and slash prompt optimization costs by up to 87%.
Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts, coupling components and obscuring credit assignment, limiting controllability, and wasting tokens. We propose Adaptive Prompt Structure Factorization (aPSF), an API-only framework (prompt-in/text-out; no access to model internals) that uses an Architect model to discover task-specific prompt structures as semantic factors. aPSF then performs interventional, single-factor updates: interventional factor-level scoring estimates each factor's marginal contribution via validation-performance changes, and error-guided factor selection routes updates to the current dominant failure source for more sample-efficient optimization. Across multiple advanced reasoning benchmarks, aPSF outperforms strong baselines including principle-aware optimizers, improving accuracy by up to +2.16 percentage points on average, and reduces optimization cost by 45--87% tokens on MultiArith while reaching peak validation in 1 step.
