CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation

TL;DR

CollabCoder introduces a dynamic collaborative framework for plan-code co-evolution in automated code generation, enhancing quality and efficiency through multi-agent decision-making.

Contribution

It proposes a novel collaborative decision-making process between plan and code modules, improving adaptability and reducing computational overhead in code generation.

Findings

Achieves 11-20% performance improvement on challenging benchmarks.

Reduces API calls by 4-10 per execution on average.

Maintains or exceeds state-of-the-art performance while being more efficient.

Abstract

Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to complex tasks. This paper introduces CollabCoder, a novel Plan-Code Co-Evolution framework that improves code generation through dynamic multi-agent collaboration. The core idea is to design a collaborative decision-making process between the plan module and the code module to decide which module should be executed for the debugging process. Extensive experiments on widely used benchmarks demonstrate that CollabCoder consistently improves code quality and robustness across tasks. Importantly, CollabCoder achieves performance comparable to or exceeding current state-of-the-art methods while reducing computational overhead, with efficiency gains becoming more pronounced as benchmark difficulty increases. On the more challenging LiveCodeBench and xCodeEval benchmarks, our approach improves performance by 11-20% over strong baselines while reducing the number of API calls by an average of 4-10 per execution.