Reproducing Recurrent Transformers: The CoTFormer
On the map: LLM reasoning → Prompting and chain-of-thought reasoning
Abstract (arXiv)
The CoTFormer architecture formalizes Chain-of-Thought as a form of recurrent latent computation, preserving intermediate states as attendable representations to mimic explicit reasoning traces. In this work, we evaluate CoTFormer and its structural variants across perplexity and compute efficiency metrics. Furthermore, we extend evaluation to controlled algorithmic settings to determine whether this recurrent framework improves out-of-distribution generalisation on inductive reasoning tasks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 6 of its 6 references that are in the map. First posted on arXiv 7 Jul 2026.
Builds on
6 of 6 references.
Closest ancestors · 1
Same direction, newest first
- 2023CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference16 Oct
Other references · 5
- 2017Attention Is All You Needcited by 59,932
- 2018Universal Transformerscited by 613
- 2025Reasoning with Latent Thoughts: On the Power of Looped Transformerscited by 223
- 2015Neural GPUs Learn Algorithmscited by 118
- 2024Language Models Need Inductive Biases to Count Inductivelycited by 25
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer
- 2026Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
- 2026Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework
- 2026J-CoT: Chain-of-Thought in J-Space
- 2025The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
- 2025To CoT or To Loop? A Formal Comparison Between Chain-of-Thought and Looped Transformers
- 2026Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs
- 2025SIM-CoT: Supervised Implicit Chain-of-Thought