Intention Chain-of-Thought Prompting with Dynamic Routing for Code Generation

TL;DR

This paper introduces RoutingGen, a dynamic prompting framework for code generation that adapts to task difficulty, guiding models to focus on core intentions and improving performance while reducing token usage.

Contribution

The paper proposes RoutingGen, a difficulty-aware routing framework with Intention Chain-of-Thought prompting, enhancing code generation by focusing on task intentions and adapting prompting strategies.

Findings

RoutingGen achieves state-of-the-art results on multiple benchmarks.

It reduces token usage by 46.37% on average.

ICoT outperforms existing prompting methods on challenging tasks.

Abstract

Large language models (LLMs) exhibit strong generative capabilities and have shown great potential in code generation. Existing chain-of-thought (CoT) prompting methods enhance model reasoning by eliciting intermediate steps, but suffer from two major limitations: First, their uniform application tends to induce overthinking on simple tasks. Second, they lack intention abstraction in code generation, such as explicitly modeling core algorithmic design and efficiency, leading models to focus on surface-level structures while neglecting the global problem objective. Inspired by the cognitive economy principle of engaging structured reasoning only when necessary to conserve cognitive resources, we propose RoutingGen, a novel difficulty-aware routing framework that dynamically adapts prompting strategies for code generation. For simple tasks, it adopts few-shot prompting; for more complex ones, it invokes a structured reasoning strategy, termed Intention Chain-of-Thought (ICoT), which we introduce to guide the model in capturing task intention, such as the core algorithmic logic and its time complexity. Experiments across three models and six standard code generation benchmarks show that RoutingGen achieves state-of-the-art performance in most settings, while reducing total token usage by 46.37% on average across settings. Furthermore, ICoT outperforms six existing prompting baselines on challenging benchmarks.