Newest papers

From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks

Taiheng Pan · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28027 · open-access PDF

Indonesian

Para praktisi menggunakan metode pembelajaran penguatan untuk model bahasa melalui kerangka kerja pelatihan, sehingga satu metode yang termasuk kerangka kerja adalah perubahan satu konfigurasi untuk pengguna. Kami mengukur seberapa sering ini terjadi. Kami melacak tujuh kerangka kerja sumber terbuka untuk pelatihan RL pasca pelatihan melalui riwayat komitmen mereka dan menghubungkan mereka ke 6.939 kertas arXiv yang diselidiki dari Januari 2025 hingga Juni 2026. Dari 1.598 kertas yang mengusulkan metode pelatihan RL umum, 37 mencapai setidaknya satu kerangka kerja.

Machine translation (Meta M2M100); the English original follows.

Abstract

Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a framework includes is one configuration change away for its users. We measure how often this happens. We trace seven open-source frameworks for RL post-training through their commit histories and link them to 6,939 screened arXiv papers from January 2025 to June 2026. Of 1,598 papers that propose a general RL training method, 37 reached at least one framework. Across five quarterly cohorts of papers, the number included within 180 days stayed between 5 and 7 while the cohorts gr

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange