mlsanityData to 7 Oct 2026

Thinking Tokens for Language Modeling

arXiv 2405.08644 ↗First posted 14 May 2024cs.CL cs.AIcited by 23

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

How much is 56 times 37? Language models often make mistakes in these types of difficult calculations. This is usually explained by their inability to perform complex reasoning. Since language models rely on large training sets and great memorization capability, naturally they are not equipped to run complex calculations. However, one can argue that humans also cannot perform this calculation immediately and require a considerable amount of time to construct the solution. In order to enhance the generalization capability of language models, and as a parallel to human behavior, we propose to use special 'thinking tokens' which allow the model to perform much more calculations whenever a complex problem is encountered.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 0 of its 18 references that are in the map. First posted on arXiv 14 May 2024.

Builds on

0 of 18 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 10.

23 papers.

Sort:

By area:

  1. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  2. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 298
  3. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoningcited by 72
  4. 2025Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifierscited by 58
  5. 2025Implicit Reasoning in Large Language Models: A Comprehensive Surveycited by 42
  6. 2026LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learningcited by 7
  7. 2024Large Language Models are Limited in Out-of-Context Knowledge Reasoningcited by 6
  8. 2024Meta-Reasoning Improves Tool Use in Large Language Modelscited by 6
  9. 2026The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Modelscited by 6
  10. 2026Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behaviorcited by 5
  11. 2025Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scalingcited by 4
  12. 2025Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Spacecited by 3
11 more
  1. 2026Capabilities and Fundamental Limits of Latent Chain-of-Thoughtcited by 3
  2. 2026From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoningcited by 3
  3. 2026Maglev: Sliding Recurrent Memorycited by 3
  4. 2024Rethinking Thinking Tokens: Understanding Why They Underperform in Practicecited by 2
  5. 2025Expanding Computation Spaces of LLMs at Inference Timecited by 2
  6. 2026SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Modelscited by 2
  7. 2026Thinking into the Future: Latent Lookahead Training for Transformerscited by 1
  8. 2026MUX: Continuous Reasoning via Multiplexed Tokenscited by 1
  9. 2025HRM-Agent: Training a recurrent reasoning model in dynamic environments using reinforcement learningcited by 0
  10. 2025Liquid Reasoning Transformers: A Sudoku-Based Prototype for Chess-Scale Algorithmic Taskscited by 0
  11. 2026Masked diffusion LLMs can use EoS tokens for hidden reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Specializing Smaller Language Models towards Multi-Step Reasoning
  2. 2024Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems
  3. 2024Counting Ability of Large Language Models and Impact of Tokenization
  4. 2024Investigating Symbolic Capabilities of Large Language Models
  5. 2023How well do Large Language Models perform in Arithmetic tasks?
  6. 2024Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
  7. 2022Limitations of Language Models in Arithmetic and Symbolic Induction
  8. 2025Large Language Models and Mathematical Reasoning Failures