# Dynamic Policy Induction for Adaptive Prompt Optimization: Bridging the Efficiency-Accuracy Gap via Lightweight Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.25267 · HTML: https://mlsanity.com/paper/2509.25267/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [SepPrune: Structured Pruning for Efficient Deep Speech Separation](https://mlsanity.com/paper/2505.12079/) (2025)
- [AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models](https://mlsanity.com/paper/2509.00039/) (2025)
- [Adaptive Optimization for Enhanced Efficiency in Large-Scale Language Model Training](https://mlsanity.com/paper/2412.04718/) (2024)
- [Selective Attention Federated Learning: Improving Privacy and Efficiency for Clinical Text Classification](https://mlsanity.com/paper/2504.11793/) (2025)
- [Gap-Filling Prompting Enhances Code-Assisted Mathematical Reasoning](https://mlsanity.com/paper/2411.05407/) (2024)

## Abstract (arXiv)

The performance of Large Language Models (LLMs) depends heavily on the chosen prompting strategy, yet static approaches such as Zero-Shot, Few-Shot, or Chain-of-Thought (CoT) impose a rigid efficiency-accuracy trade-off. Highly accurate strategies like Self-Consistency (SC) incur substantial computational waste on simple tasks, while lightweight methods often fail on complex inputs. This paper introduces the Prompt Policy Network (PPN), a lightweight reinforcement learning framework that formalizes adaptive strategy selection as a single-step Markov Decision Process (MDP). The PPN, trained with Proximal Policy Optimization (PPO) and guided by a resource-explicit reward function, learns to allocate costly reasoning strategies only when necessary. Experiments on arithmetic reasoning benchmarks demonstrate that PPN achieves superior performance on the efficiency-accuracy Pareto front, delivering up to 61.5% token cost reduction compared to Self-Consistency while maintaining competitive accuracy. This work contributes a systematic, adaptive framework for cost-efficient LLM deployment, advancing the design of lightweight optimization techniques for scalable and sustainable language model applications.