AI Science Tracker
EN

No More Import Errors: Constrained Decoding for Guaranteed Valid Imports in LLM-Generated Tests

Affiliation not stated in the reviewed material · 30 Oct 2026 · computer science

Discovery

No More Import Errors: Constrained Decoding for Guaranteed Valid Imports in LLM-Generated Tests

Source check: Source checked. Not independent scientific confirmation.

Finding / tested result: The study identifies import streaks as a failure mode of greedy constrained decoding and tests CBDL, which reduces invalid imports and improves the fraction of correct generated tests in the reported Python/Java tasks.

Technology: grammar-constrained decoding plus beam/lookup selection controls import tokens in LLM-generated tests.

Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
grammar-constrained decoding plus beam/lookup selection controls import tokens in LLM-generated tests.
Limitation / still unknown
two test-generation tasks, Python and Java implementations, static/dynamic baselines and functional-correctness outcomes
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://arxiv.org/html/2610.41878v1

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse computer science discoveries.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.