{"slug": "gac-noise-aware-adaptive-mixing-for-hybrid-sft-rl-post-training", "title": "GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training", "summary": "Researchers have developed GAC, a noise-aware adaptive mixing controller for hybrid post-training that combines supervised fine-tuning and reinforcement learning. The method dynamically adjusts the mixing weight between the two training signals based on online estimates of gradient variance and disagreement, replacing fixed schedules that cannot adapt to changing noise levels. Experiments across math, code, science, and logic benchmarks showed GAC consistently outperformed fixed and rule-based baselines with less than 1% training overhead, with larger gains at bigger model scales.", "body_md": "# Computer Science > Machine Learning\n\n[Submitted on 25 May 2026]\n\n# Title:GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training\n\n[View PDF](/pdf/2605.26184)\n\n[HTML (experimental)](https://arxiv.org/html/2605.26184v1)\n\nAbstract:Hybrid post-training usually combines supervised fine-tuning and reinforcement learning, but fixed mixing schedules cannot adapt when the relative noise of the two signals changes over time. We propose GAC, a noise-aware controller that derives an adaptive mixing weight from online estimates of gradient variance and disagreement between the two training signals. The method adds smoothing, prior guidance, and bounded updates while reusing existing training tensors. Experiments on math, code, science, and logic benchmarks show that GAC consistently improves hybrid post-training over strong fixed and rule-based baselines, with larger gains at larger model scales and less than 1% training overhead.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/gac-noise-aware-adaptive-mixing-for-hybrid-sft-rl-post-training", "canonical_source": "https://arxiv.org/abs/2605.26184", "published_at": "2026-05-27 04:00:00+00:00", "updated_at": "2026-05-27 04:29:09.622071+00:00", "lang": "en", "topics": ["machine-learning", "large-language-models", "artificial-intelligence"], "entities": ["GAC"], "alternates": {"html": "https://wpnews.pro/news/gac-noise-aware-adaptive-mixing-for-hybrid-sft-rl-post-training", "markdown": "https://wpnews.pro/news/gac-noise-aware-adaptive-mixing-for-hybrid-sft-rl-post-training.md", "text": "https://wpnews.pro/news/gac-noise-aware-adaptive-mixing-for-hybrid-sft-rl-post-training.txt", "jsonld": "https://wpnews.pro/news/gac-noise-aware-adaptive-mixing-for-hybrid-sft-rl-post-training.jsonld"}}