GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
The paper presents GAC, a noise-aware adaptive mixing method for hybrid post-training in machine learning. This approach addresses the limitations of fixed mixing schedules by adapting to changes in the noise levels of training signals. Experimental results demonstrate that GAC significantly enhances performance on various benchmarks with minimal training overhead.
- ▪GAC derives adaptive mixing weights from online estimates of gradient variance and disagreement between training signals.
- ▪The method incorporates smoothing, prior guidance, and bounded updates while reusing existing training tensors.
- ▪Experiments show that GAC consistently outperforms strong fixed and rule-based baselines, especially with larger model scales.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.26184 |
| Publication time | Wed, 27 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-27T04:07:56.398Z |
| Last seen | 2026-05-27T04:07:56.398Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | dVf44_IHNEiX |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2605.26184 (cs) [Submitted on 25 May 2026] Title:GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training Authors:Yuelin Hu, Zhenbo Yu, Zhengxue Cheng, Wei Liu, Li Song View a PDF of the paper titled GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training, by Yuelin Hu and 4 other authors View PDF HTML (experimental) Abstract: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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
