Search

huggingface.co › papers › 2605.31058

Paper page - Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination

… Prior studies often rely on heuristic seed expansion s for data synthesis, which severely limits both novelty and difficulty. …

Jun 5, 2026

huggingface.co › papers › 2605.00754

Paper page - Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring

… To this end, we first compile Themis-CodeRewardBench, a benchmark to evaluate code RMs across five preference dimensions i.e., criteria and eight programming languages, on which we profile 50+ code, math, and general-purpose RMs. …

May 4, 2026