Pith. sign in

REVIEW 8 cited by

HardTests: Synthesizing High-Quality Test Cases for LLM Coding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.24098 v1 pith:456F6KSN submitted 2025-05-30 cs.CL

classification cs.CL
keywords hardtestshigh-qualitypipelinepointsproblemstestscasescode
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Verifiers play a crucial role in large language model (LLM) reasoning, needed by post-training techniques such as reinforcement learning. However, reliable verifiers are hard to get for difficult coding problems, because a well-disguised wrong solution may only be detected by carefully human-written edge cases that are difficult to synthesize. To address this issue, we propose HARDTESTGEN, a pipeline for high-quality test synthesis using LLMs. With this pipeline, we curate a comprehensive competitive programming dataset HARDTESTS with 47k problems and synthetic high-quality tests. Compared with existing tests, HARDTESTGEN tests demonstrate precision that is 11.3 percentage points higher and recall that is 17.5 percentage points higher when evaluating LLM-generated code. For harder problems, the improvement in precision can be as large as 40 points. HARDTESTS also proves to be more effective for model training, measured by downstream code generation performance. We will open-source our dataset and synthesis pipeline at https://leililab.github.io/HardTests/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    Introduces the Generalization Spectrum evaluation framework to track per-example generalization across transfer distances in competitive programming tasks.

  2. FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale

    cs.LG 2026-05 conditional novelty 7.0 of 10

    FrontierSmith automates synthesis of open-ended coding problems from closed-ended seeds and shows measurable gains on two open-ended LLM coding benchmarks.

  3. Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch

    cs.SE 2026-08 conditional novelty 6.0 of 10

    A target-blind agent-generated test suite with a consensus-and-validator certification chain found 906 verified accepted-but-buggy submissions on AtCoder and led all baselines on post-cutoff Codeforces problems.

  4. The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    The Generalization Spectrum framework shows RL turns memorization into near-transfer more efficiently than SFT, ICL transfer depends on correspondence, and local gains often fail to expand far-transfer radius.

  5. VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation

    cs.SE 2026-05 unverdicted novelty 6.0 of 10

    VeriContest supplies 946 problems with specs, code, proofs, and tests to benchmark verifiable code generation in Rust/Verus, showing models reach 92% on code but only 5% end-to-end on full verifiable synthesis.

  6. Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems

    cs.RO 2026-04 unverdicted novelty 6.0 of 10

    Waypoint-based bi-level planning with curriculum RLVR improves multi-robot task success rates in dense-obstacle benchmarks over motion-agnostic and VLA baselines.

  7. Efficiency of turbulence

    physics.flu-dyn 2025-08 unverdicted novelty 6.0 of 10

    The efficiency of turbulence, the fraction of input energy stored in the flow, appears bounded and may saturate in a power-law manner across several turbulent flows.

  8. CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming

    cs.CL 2026-05 unverdicted novelty 5.0 of 10

    CP-Agent improves LLM competitive programming performance via calibrated feedback mechanisms that target false-admission risk, evidence against bad programs, and success hazard.

Pith tools