ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training
Source published ·Modelwire updated
Original coverage: arXiv cs.LG ↗·How Modelwire adds context
The development
Reasoning models face a deployment bottleneck: full-precision inference is expensive, yet aggressive quantization to 4-bit formats degrades chain-of-thought accuracy. ReQAT addresses this by identifying that quantization errors concentrate on low-entropy tokens (digits, operators) where noise cascades through multi-step reasoning. The framework uses trace-aligned quantization-aware training to preserve symbolic precision while compressing weights, activations, and KV caches to FP4. This work matters because it unlocks efficient deployment of long-reasoning models without sacrificing correctness, directly impacting the feasibility of on-device or cost-constrained inference for problem-solving tasks.
Modelwire’s AI-generated summary of coverage from arXiv cs.LG.
Modelwire analysis
ExplainerOur AI-generated reading of the wider context and the next developments to watch.
The key insight buried in the methodology is that quantization damage is not uniformly distributed across tokens. Digits and operators, precisely the tokens that carry logical weight in chain-of-thought, are low-entropy and therefore most sensitive to rounding noise, meaning a generic compression scheme will systematically corrupt the steps that matter most.
This sits alongside a broader wave of inference-time efficiency work appearing in the archive this week. The MoE pruning paper ('How to Score Experts for One-Shot MoE Expert Pruning') addresses a structurally similar problem: models that are theoretically deployable but practically bottlenecked by memory and compute at inference time. Both papers are pushing toward the same operational goal from different angles, one through weight sparsity, the other through numerical precision. Neither alone solves deployment for the largest reasoning models, and the interaction between expert pruning and quantization in combined pipelines remains an open question the current literature does not address.
Watch whether ReQAT's FP4 accuracy claims hold on MATH-500 and GPQA Diamond under third-party replication, particularly on problems requiring more than 16 reasoning steps, where quantization error has the most opportunity to compound.
This interpretation is generated from the summary above and the archive coverage cited below. Our methodology · Report an error
Coverage behind this analysis
These archive entries ground the connection in our analysis. They are ordered by source publication date, with links to our coverage and the original sources.
·arXiv cs.LG
How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle
Researchers propose a unified framework for pruning experts in Mixture-of-Experts language models, addressing a critical deployment bottleneck. Current MoE systems reduce inference cost through sparse activation but still require storing all experts in memory, limiting practical deployment. This work systematizes expert selection around three dimensions: routing frequency, gate weighting, and activation strength, then derives principles…
MentionsReQAT · Large Reasoning Models · FP4 · Trace-Aligned QAT
How this coverage is produced
Modelwire uses AI to generate summaries and context from source headlines, snippets, and selected archive coverage. Automated checks do not verify every claim, and items are not routinely reviewed by a person before publication. Zacaria Solis operates the site. Read the linked source for the full evidence and report errors through our corrections process.
Modelwire summarizes, we don’t republish. The full content lives on arxiv.org. If you’re a publisher and want a different summarization policy for your work, see our takedown page.