GraphAHA: Graph-Based Adaptive Search with Heterogeneous Actions for Test-Time Code Generation

2026-09-11

AI Summary

为解决代码生成中预算分配与状态依赖问题，提出GraphAHA方法，通过图结构搜索和异构动作选择优化测试时代码生成。

Abstract

Test-time scaling improves code generation by spending additional inference budget (e.g., calls or tokens) on direct sampling, feedback-conditioned repair, and reasoning-guided implementation. Search-based methods can allocate this budget adaptively, but two challenges remain. First, tree-structured search treats each generation history as a separate state even when trajectories converge to the same program, duplicating evaluation and preventing statistics from being shared. Second, sampling, repair, and reasoning have complementary and state-dependent payoffs, making online allocation among them difficult under a finite budget. To address these challenges, we propose an adaptive graph search method with heterogeneous actions (GraphAHA). GraphAHA organizes the test-time code generation in a typed directed acyclic graph. Equivalent programs are merged into a single code node, allowing their downstream search statistics to be reused across all discovery paths. Hierarchical Thompson sampling then selects whether to generate a new state or follow an existing successor and, for generation, chooses among the type-valid sampling, reasoning, implementation, and repair operations. Evaluated on LiveCodeBench and CodeContests with Qwen2.5-Coder and DeepSeek-Coder, GraphAHA achieves the best score in 18 of 20 cases. For Pass@1 measured using visible tests, it outperforms the strongest baseline for both models on both benchmarks by 4.1 percentage points on average, demonstrating more effective use of a fixed inference budget.

Problem

• code generation
• inference budget
• search-based methods
• tree-structured search
• adaptive allocation

Innovation

• Graph-Based Adaptive Search
• Heterogeneous Actions
• Typed Directed Acyclic Graph
• Hierarchical Thompson Sampling
• Test-Time Code Generation