mlsanityData to 14 Oct 2026

DeepThink: A Conceptual Model for Knowledge-Addressable Recurrent Language Modeling

arXiv 2610.16171 ↗First posted 12 Oct 2026cs.CLcited by 0

On the map: LLM reasoning → Test-time compute and efficient thinking also fits: Reasoning benchmarks and evaluation

Abstract (arXiv)

This manuscript presents DeepThink, a knowledge-addressable framework for recurrent language modeling. A Knowledge Bank stores typed Knowledge Units, a Knowledge Activator selects units from the current execution state, Knowledge Assembly produces an executable configuration, and a Shared Thinking Operator updates that state. An output stage then organizes generation. This organization exposes knowledge capacity, activation width, and recurrent depth as separate design variables, supporting both complete parameter packages and fine-grained expert or low-rank modules. We formalize the interfaces and their execution semantics, including state-dependent selection, parameter-space assembly, and thinking followed by generation. For compatible templates and complete runtime-state configurations, we establish an exact Fixed-Schedule Realization of an existing fixed-depth model. Exact shared-base reparameterization and pretrained output-tail reuse provide complementary initialization constructions. Together, these results define a route from pretrained models to dynamically selected and assembled recurrent computation. A synthesis of conditional computation, recurrent models, modular parameters, and knowledge interfaces positions DeepThink within the research landscape and identifies the design questions arising from their integration.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 25 of its 32 references that are in the map. First posted on arXiv 12 Oct 2026.

Builds on

25 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach7 Feb

Other references · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  6. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  7. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
  8. 2016HyperNetworkscited by 1,027
  9. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 867
  10. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  11. 2016Adaptive Computation Time for Recurrent Neural Networkscited by 506
  12. 2023LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Compositioncited by 364
12 more
  1. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 319
  2. 2024MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Expertscited by 147
  3. 2025Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computationcited by 133
  4. 2019Large Memory Layers with Product Keyscited by 124
  5. 2023Soft Merging of Experts with Adaptive Routingcited by 90
  6. 2024Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRAcited by 78
  7. 2024Mixture of A Million Expertscited by 72
  8. 2024MoEUT: Mixture-of-Experts Universal Transformerscited by 59
  9. 2024MeteoRA: Multiple-tasks Embedded LoRA for Large Language Modelscited by 16
  10. 2025Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Modelscited by 9
  11. 2026MoRE: Mixture of Reused Expertscited by 3
  12. 2026Fixed Universal Transformerscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models
  2. 2026Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework
  3. 2026Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs
  4. 2026CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models
  5. 2026Think, But Don't Overthink: Reproducing Recursive Language Models
  6. 2026RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language Models
  7. 2025ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
  8. 2026Allocating Recurrent Compute in Looped Language Models