cs.CLMay 30, 2025

HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithmic Coding

Authors: Zhongmou He, Yee Man Choi, Kexun Zhang, Jiabao Ji, Junting Zhou, Dejia Xu, Ivan Bercovich, Aidan Zhang, 

Organizations: Carnegie Mellon University · UC Santa Barbara · UT Austin

Abstract

Verifiers provide important reward signals for reinforcement learning of large language models (LLMs). However, it is challenging to develop or create reliable verifiers, especially for code generation tasks. A well-disguised wrong solution program may only be detected by carefully human-written edge cases that are difficult to synthesize automatically. To address this issue, we propose HARDTESTGEN, an approach to synthesize high-quality test cases for algorithmic coding problems. We curate a comprehensive algorithmic programming dataset HARDTESTS with 26.6k problems and high-quality synthetic tests. Compared with existing tests, HARDTESTGEN tests demonstrate significantly higher accuracy in verifying LLM-generated code (+11.22 percentage points in precision, the percentage of actually correct code within the predicted correct ones). We also show that downstream post-training -- including rejection sampling and reinforcement learning (RL) -- using HARDTESTS verifier results in improved performance of LLM code generation. We open-source our dataset and synthesis pipeline at https://leililab.github.io/HardTests/.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval

    Oct 1, 2026Nickil Maveli, Antonio Vergari, Shay B. CohenCode Generation EvaluationCode Generation Benchmarks

  2. Confidence-Gated Transductive Test Generation for Code Reranking

    Sep 11, 2026Sungjae Lee, Youngsik Yoon, Seockbean Song +3LLM RerankingAutomated Test Generation