mlsanityData to 14 Oct 2026

LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss

arXiv 2605.08755 ↗First posted 9 May 2026cs.LGcited by 1

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primary deployment concern. Weight quantization is the standard tool for acceleration, but representative recipes -- including state-of-the-art end-to-end (E2E) QAT -- lose accuracy on long-decoding reasoning benchmarks despite preserving perplexity and short-decode accuracy. Through a systematic gradient-direction analysis, we identify two factors driving this gap: (i) KV-cache fidelity preservation under the QAT loss, which E2E supervision attenuates via the softmax Fisher metric; and (ii) Hessian-subspace alignment between calibration data and the deployment distribution. We propose LookAhead Quantization (LAQuant), a layer-wise weight-only QAT method that addresses both factors without online-transform overhead by combining reasoning-domain calibration with a one-layer lookahead loss whose implicit cross-layer co-adaptation preserves the next-layer residual stream. For Qwen3-4B under W3G128 quantization, LAQuant improves AIME25 Pass@1 over ParoQuant by 15.11pp (1.93pp over ParoQuant++ at matched calibration) while achieving a 3.42x decoding speedup over FP16 on RTX A6000, compared with ParoQuant's 3.01x.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 46 of its 56 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

46 of 56 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals31 Jan
  2. 2026What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study21 Jan
  3. 2025ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference13 Nov
  4. 2025Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models7 Apr
  5. 2025s1: Simple test-time scaling31 Jan
  6. 2025Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning6 Jan

Other references · 40

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2025Qwen3 Technical Reportcited by 8,820
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  6. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  7. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  8. 2016Pointer Sentinel Mixture Modelscited by 3,096
  9. 2015Fast R-CNNcited by 2,933
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  11. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  12. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
28 more
  1. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  2. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  3. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  4. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  5. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
  6. 2024SpinQuant: LLM quantization with learned rotationscited by 471
  7. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 424
  8. 2022Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruningcited by 322
  9. 2023SqueezeLLM: Dense-and-Sparse Quantizationcited by 294
  10. 2023Atom: Low-bit Quantization for Efficient and Accurate LLM Servingcited by 272
  11. 2024QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Servingcited by 208
  12. 2023BitNet: Scaling 1-bit Transformers for Large Language Modelscited by 189
  13. 2024RedPajama: an Open Dataset for Training Large Language Modelscited by 182
  14. 2024DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMscited by 167
  15. 2024BiLLM: Pushing the Limit of Post-Training Quantization for LLMscited by 144
  16. 2024EfficientQAT: Efficient Quantization-Aware Training for Large Language Modelscited by 127
  17. 2024QTIP: Quantization with Trellises and Incoherence Processingcited by 91
  18. 2024BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillationcited by 84
  19. 2023On the Impact of Calibration Data in Post-training Quantization and Pruningcited by 58
  20. 2024VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Modelscited by 57
  21. 2021AR-LSAT: Investigating Analytical Reasoning of Textcited by 51
  22. 2024DB-LLM: Accurate Dual-Binarization for Efficient LLMscited by 37
  23. 2025An Empirical Study of Qwen3 Quantizationcited by 21
  24. 2024Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levelscited by 16
  25. 2024HadaCore: Tensor Core Accelerated Hadamard Transform Kernelcited by 12
  26. 2025Does quantization affect models' performance on long-context tasks?cited by 10
  27. 2024RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracycited by 9
  28. 2025The Impact of Quantization on Large Reasoning Model Reinforcement Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Quantizing Recursive Reasoning Modelscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training
  2. 2025MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning
  3. 2026KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
  4. 2026Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery
  5. 2026Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
  6. 2026Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization
  7. 2026RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models
  8. 2025Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models