Reasoning Primitives in Hybrid and Non-Hybrid LLMs

• URL: http://arxiv.org/abs/2604.21454v1
• Date: Thu, 23 Apr 2026 09:13:28 GMT
• Title: Reasoning Primitives in Hybrid and Non-Hybrid LLMs
• Abstract summary: We study reasoning through two primitives, recall and state-tracking.<n>We use matched Olmo3 transformer and hybrid models in instruction-tuned and reasoning-augmented variants.
• Score: 10.629439705877054
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning in large language models is often treated as a monolithic capability, but its observed gains may arise from more basic operations. We study reasoning through two such primitives, recall and state-tracking, and ask whether hybrid architectures that combine attention-based retrieval with recurrent state updates are better suited than attention-only models for tasks that jointly require both. Using matched Olmo3 transformer and hybrid models in instruction-tuned and reasoning-augmented variants, we evaluate these models on a set of controlled tasks involving a mixture of state-tracking and recall primitives, state-based recall. Across tasks, we notice that reasoning augmentation provides the largest overall improvement, substantially extending the range of difficulty over which models remain effective. We also notice that in certain tasks, the hybrid reasoning model remains substantially more robust as sequential dependence increases. In contrast, the transformer reasoning model degrades sharply in performance as task difficulty increases beyond a given threshold. These results suggest that reasoning tokens and architectural inductive biases contribute at different levels of the computational process: explicit reasoning can expand a model's effective operating range, but its benefit depends on how well the underlying architecture supports persistent state propagation. Given the small size of our case study, which involves a limited set of models and tasks, we present these findings as suggestive rather than conclusive and leave broader validation across model families, scales, and task variations to future work.

Related papers

• Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models [50.45915413315706]
  We prove the existence of fundamental limitations for non-hybrid models.<n>We construct hybrid models of small size and working memory that provably solve these tasks.<n>We additionally demonstrate that hybrid models exhibit stronger length generalization and out-of-distribution robustness than non-hybrids.
  arXiv  Detail & Related papers  (2026-03-09T19:20:01Z)
• Architecture Decoupling Is Not All You Need For Unified Multimodal Model [64.19284951218098]
  We propose Attention Interaction Alignment (AIA) loss, which explicitly learns Task-Specific multimodal interaction patterns during training.<n>AIA not only refines cross-modal attention patterns, but also boosts both generation and understanding performance.
  arXiv  Detail & Related papers  (2025-11-27T17:55:25Z)
• Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models [44.17697803306198]
  We introduce textitCodeSeq, a synthetic post-training dataset built from number sequences.<n>Our pipeline generates supervised fine data by reflecting on failed test cases and incorporating iterative corrections.<n> Experimental results show that the models trained with textitCodeSeq improve on various reasoning tasks and can preserve the models' OOD performance.
  arXiv  Detail & Related papers  (2025-10-16T12:29:40Z)
• Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling [60.63703438729223]
  We show how different architectures and training methods affect model multi-step reasoning capabilities.<n>We confirm that increasing model depth plays a crucial role for sequential computations.
  arXiv  Detail & Related papers  (2025-08-22T18:57:08Z)
• Frugal Incremental Generative Modeling using Variational Autoencoders [4.7881638074901955]
  We develop a novel replay-free incremental learning model based on Variational Autoencoders (VAEs)<n>The proposed method considers two variants of these VAEs: static and dynamic with no (or at most a controlled) growth in the number of parameters.
  arXiv  Detail & Related papers  (2025-05-28T14:37:57Z)
• Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models [26.005367102695317]
  Multimodal Large Language Models can exhibit difficulty in distinguishing task-relevant from irrelevant signals.<n>We show that spurious information from irrelevant modalities often leads to significant performance degradation.<n>We propose a novel framework to finetune MLLMs, including perturbation-based data augmentation with both perturbations and adversarial perturbations.
  arXiv  Detail & Related papers  (2025-05-26T07:31:32Z)
• Modèles de Substitution pour les Modèles à base d'Agents : Enjeux, Méthodes et Applications [0.0]
  Agent-based models (ABM) are widely used to study emergent phenomena arising from local interactions.<n>The complexity of ABM limits their feasibility for real-time decision-making and large-scale scenario analysis.<n>To address these limitations, surrogate models offer an efficient alternative by learning approximations from sparse simulation data.
  arXiv  Detail & Related papers  (2025-05-17T08:55:33Z)
• Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead [33.011660907969706]
  Inference-time scaling can enhance the reasoning capabilities of large language models.<n>We investigate the benefits and limitations of scaling methods across nine state-of-the-art models and eight challenging tasks.
  arXiv  Detail & Related papers  (2025-03-31T23:40:28Z)
• Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks [50.75902473813379]
  This work introduces a comprehensive evaluation framework that systematically examines the role of instructions and inputs in the generalisation abilities of such models. The proposed framework uncovers the resilience of multimodal models to extreme instruction perturbations and their vulnerability to observational changes.
  arXiv  Detail & Related papers  (2024-07-04T14:36:49Z)
• Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models [80.23791222509644]
  Inconsistent AI models are considered brittle and untrustworthy by human users. We find that state-of-the-art vision-language models suffer from a surprisingly high degree of inconsistent behavior across tasks. We propose a rank correlation-based auxiliary training objective, computed over large automatically created cross-task contrast sets.
  arXiv  Detail & Related papers  (2023-03-28T16:57:12Z)
• Reinforcement Learning as One Big Sequence Modeling Problem [84.84564880157149]
  Reinforcement learning (RL) is typically concerned with estimating single-step policies or single-step models. We view RL as a sequence modeling problem, with the goal being to predict a sequence of actions that leads to a sequence of high rewards.
  arXiv  Detail & Related papers  (2021-06-03T17:58:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.