mlsanityData to 7 Oct 2026

YANchor-4B: Effective Long-Horizon Reasoning in O(N) Time with O(1) Memory

arXiv 2610.10118 ↗First posted 7 Oct 2026cs.LG cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Long-horizon reasoning demands access to earlier information at a manageable generation cost. Full-history attention incurs growing storage and computation, while recurrent compression can lose precise details. Therefore, we present YANchor-4B, a general-purpose recurrent model that preserves crucial memory as ANchors for retrieval during subsequent reasoning. Beyond O(N)-time generation and O(1) memory, YANchor enables effective long-horizon reasoning through its multidimensional memory mechanism. For example, on challenging math problems, it achieves 82.93% mean pass@1 on AIME 2024--2026 and 63.64% on HMMT, substantially outperforming linear-time, constant-state counterparts, including larger models. It also delivers several-fold higher batched long-generation throughput than Transformer and hybrid baselines on H100. Furthermore, evaluations across dozens of benchmarks demonstrate YANchor's superiority in general-purpose capabilities.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 54 references that are in the map. First posted on arXiv 7 Oct 2026.

Builds on

38 of 54 references.

References · 38

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  4. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  7. 2023Let's Verify Step by Stepcited by 3,598
  8. 2021Program Synthesis with Large Language Modelscited by 3,509
  9. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  10. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  11. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  12. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
26 more
  1. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  2. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  3. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  4. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  5. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  6. 2016A Diagram Is Worth A Dozen Imagescited by 793
  7. 2023C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Modelscited by 694
  8. 2024Gated Delta Networks: Improving Mamba2 with Delta Rulecited by 483
  9. 2023CMMLU: Measuring massive multitask language understanding in Chinesecited by 436
  10. 2024xLSTM: Extended Long Short-Term Memorycited by 320
  11. 2023MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoningcited by 195
  12. 2019WinoGrande: An Adversarial Winograd Schema Challenge at Scalecited by 194
  13. 2024Are We Done with MMLU?cited by 178
  14. 2025Generalizing Verifiable Instruction Followingcited by 178
  15. 2024Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modelingcited by 167
  16. 2025RWKV-7 "Goose" with Expressive Dynamic State Evolutioncited by 134
  17. 2025BIG-Bench Extra Hardcited by 123
  18. 2025SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplinescited by 67
  19. 2024RecurrentGemma: Moving Past Transformers for Efficient Open Language Modelscited by 61
  20. 2025RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scalecited by 24
  21. 2025xLSTM 7B: A Recurrent LLM for Fast and Efficient Inferencecited by 17
  22. 2025Artificial Hippocampus Networks for Efficient Long-Context Modelingcited by 9
  23. 2026A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgetscited by 4
  24. 2025Scaling Reasoning without Attentioncited by 3
  25. 2026Super Apriel: One Checkpoint, Many Speedscited by 1
  26. 2026On Subquadratic Architectures: From Applications to Principlescited by 1

Built on by

Not cited yet.