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

ACL ARR 2026 January Submission2858 Authors

Keywords: Code Generation, Plan–Code Co-Evolution, Multi-Agent LLMs; Collaborative Decision Making; Dynamic Planning, Self-Improving Debugging

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.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: NLP Applications, Language Modeling

Contribution Types: Model analysis & interpretability, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 2858