{"slug": "selective-left-shift-turning-test-time-compute-and-difficulty-based-curation-for", "title": "Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation", "summary": "Researchers propose a three-phase pipeline to improve small language models for low-resource programming languages like Julia and Ballerina, achieving up to +14.2 points on pass@1 metrics while reducing data and cost by two-thirds and six-fold respectively. The method decouples syntax acquisition from algorithmic reasoning by left-shifting inference-time compute to offline data synthesis, followed by supervised fine-tuning and reinforcement learning with verifiable rewards.", "body_md": "arXiv:2607.07748v1 Announce Type: new\nAbstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia. Improving Small Language Models~(SLMs) for these languages faces a trilemma: Supervised Fine-Tuning~(SFT) is bottlenecked by data scarcity, inference-time scaling is too expensive for deployment, and Reinforcement Learning from scratch yields near zero advantages. We propose a three-phase pipeline that resolves this trilemma by decoupling syntax acquisition from algorithmic reasoning. First, we \\emph{left-shift} inference-time compute to an offline data synthesis engine that uses iterative compiler and test feedback to generate verified training examples. Second, we fine-tune an SLM on this synthetic, verified data to embed strong syntactic priors. Third, we apply Reinforcement Learning with Verifiable Reward~(RLVR) grounded by language-agnostic Input/Output tests, where the SFT prior constrains exploration away from syntax errors. Applied to Qwen3-8B, our pipeline improves pass@1 by up to +7.6 points on MultiPL-E and +14.2 points on the Agnostics LiveCodeBench for Julia compared to SOTA results. Furthermore, the pipeline only used $\\frac{1}{3}$ data and $\\frac{1}{6}$ cost over the previous state-of-the-art. We further demonstrate that the pipeline generalizes to Ballerina achieving 49.7\\% MultiPL-E Pass@1, a language with near-zero pretraining representation. Ablations confirm that both the SFT phase and execution-grounded rewards are necessary for stable training.", "url": "https://wpnews.pro/news/selective-left-shift-turning-test-time-compute-and-difficulty-based-curation-for", "canonical_source": "https://arxiv.org/abs/2607.07748", "published_at": "2026-07-10 04:00:00+00:00", "updated_at": "2026-07-10 04:16:44.443761+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "machine-learning", "ai-research", "developer-tools"], "entities": ["Qwen3-8B", "MultiPL-E", "Agnostics LiveCodeBench", "Julia", "Ballerina"], "alternates": {"html": "https://wpnews.pro/news/selective-left-shift-turning-test-time-compute-and-difficulty-based-curation-for", "markdown": "https://wpnews.pro/news/selective-left-shift-turning-test-time-compute-and-difficulty-based-curation-for.md", "text": "https://wpnews.pro/news/selective-left-shift-turning-test-time-compute-and-difficulty-based-curation-for.txt", "jsonld": "https://wpnews.pro/news/selective-left-shift-turning-test-time-compute-and-difficulty-based-curation-for.jsonld"}}