BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations
This addresses the challenge of reliable automated code generation for developers, though it is an incremental improvement over prior multi-agent frameworks.
The paper tackles the problem of fragile test generation in LLM-based code synthesis by introducing BACE, a Bayesian co-evolutionary framework that evolves code and test populations with belief updates, achieving superior performance on LiveCodeBench v6 with concrete gains across proprietary and open-weight models.
Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. While an interactive feedback loop can improve performance, writing effective tests is a non-trivial task. Early multi-agent frameworks, such as AgentCoder, automated this process but relied on generated tests as absolute ground truth. This approach is fragile: incorrect code frequently passes faulty or trivial tests, while valid solutions are often degraded to satisfy incorrect assertions. Addressing this limitation, newer methods have largely abandoned test generation in favor of planning and reasoning based on examples. We argue, however, that generated tests remain a valuable signal if we model them as noisy sensors guided by bayesian updates. To this end, we introduce BACE (Bayesian Anchored Co-Evolution), a framework that reformulates synthesis as a Bayesian co-evolutionary process where code and test populations are evolved, guided by belief distributions that are reciprocally updated based on noisy interaction evidence. By anchoring this search on minimal public examples, BACE prevents the co-evolutionary drift typical of self-validating loops. Extensive evaluations on LiveCodeBench v6 (post-March 2025) reveal that BACE achieves superior performance across both proprietary models and open-weight small language models.