arXiv Machine Learning
Jun 10
CodeAlchemy: Synthetic Code Rewriting at Scale
arXiv:2606. 10087v1 Announce Type: cross Abstract: Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats.
Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation
arXiv:2607. 07748v1 Announce Type: new Abstract: 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.
Related stories
arXiv Machine Learning
Aug 4
Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language
arXiv:2605. 15607v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly understood.
arXiv AI
Jul 20
Understanding Reasoning from Pretraining to Post-Training
arXiv:2607. 16097v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it.
arXiv AI
Jun 16
Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
arXiv:2510. 13940v4 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency.
arXiv Machine Learning
Jul 3
DecompRL: Solving Harder Problems by Learning Modular Code Generation
arXiv:2607. 02390v1 Announce Type: new Abstract: How can Large Language Models (LLMs) solve problems they currently cannot?
arXiv AI
Jun 16
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
arXiv:2511. 08577v3 Announce Type: replace-cross Abstract: Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications.
arXiv Machine Learning
Jul 24
Domyn-Small: A European 10B Reasoning Language Model
arXiv:2607. 20448v1 Announce Type: cross Abstract: We introduce Domyn-Small, a 10-billion-parameter open-weight reasoning language model released under the MIT license.
arXiv AI
Jun 18
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier
arXiv:2606. 18284v1 Announce Type: cross Abstract: The limiting resource for training agents via reinforcement learning (RL) is increasingly frontier task supply: valid, solvable tasks just difficult enough to train the current model.
arXiv Machine Learning
Jun 24
Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
arXiv:2603. 15510v2 Announce Type: replace Abstract: The synthesis of inductive loop invariants remains a critical bottleneck in automated program verification.
arXiv AI
Jun 26
NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research
arXiv:2606. 26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization.
arXiv AI
Jul 28
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
arXiv:2509. 03059v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and programming, where ground-truth correctness can be automatically evaluated.
arXiv AI
Jun 3
Aletheia: What Makes RLVR For Code Verifiers Tick?
arXiv:2601. 12186v3 Announce Type: replace-cross Abstract: Multi-domain thinking verifiers trained via Reinforcement Learning with Verifiable Rewards (RLVR) are a cornerstone of modern post-training.