Search papers, labs, and topics across Lattice.
The paper introduces SEMAG, a self-evolutionary multi-agent framework for code generation that dynamically adapts its workflow and backbone model based on task complexity. SEMAG decomposes coding tasks into planning, coding, debugging, and discussion stages, allowing agents to access and upgrade to the latest LLMs in real-time. Experiments demonstrate that SEMAG achieves state-of-the-art Pass@1 accuracy, outperforming existing methods by 3.3% on CodeContests with identical backbones and reaching 52.6% with self-evolutionary model selection.
Forget fixed workflows: SEMAG's self-evolving agents dynamically adapt their coding process and even upgrade their backbone LLM, leading to state-of-the-art code generation performance.
Large Language Models (LLMs) have made significant progress in handling complex programming tasks. However, current methods rely on manual model selection and fixed workflows, which limit their ability to adapt to changing task complexities. To address this, we propose SEMAG, a Self-Evolutionary Multi-Agent code Generation framework that mimics human coding practices. It decomposes programming tasks into stages, including planning, coding, debugging, and discussion, while adapting workflows to task difficulty. Its self-evolutionary agents can access the latest models in real time and automatically upgrade the backbone model. SEMAG sets new state-of-the-art Pass@1 accuracy across benchmarks. Using identical backbone models, SEMAG outperforms prior methods by 3.3% on CodeContests. When augmented with self-evolutionary model selection that automatically identifies optimal backbones, SEMAG reaches 52.6%, showcasing both framework effectiveness and adaptability to evolving LLM capabilities.
