Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
cs.CL
Submitted: 2025-05-22
Updated: 2026-08-31
Comments: EMNLP 2026 Findings
Code: https://github.com/EIT-NLP/Awesome-Latent-CoT
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning.
Terminology
Abstract
Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT relies on explicitly verbalized intermediate steps, which constrains its broader applicability, particularly in abstract reasoning tasks beyond language. To address this, there has been growing research interest in latent CoT reasoning, where the reasoning process is embedded within latent spaces. By decoupling reasoning from explicit language generation, latent CoT offers the promise of richer cognitive representations and facilitates more flexible, faster inference. This paper aims to present a comprehensive overview of this emerging paradigm and establish a systematic taxonomy. We analyze recent advances in methods, categorizing them from token-wise horizontal approaches to layer-wise vertical strategies. We then provide in-depth discussions of these methods, highlighting their design principles, applications, and remaining challenges. We hope that our survey provides a structured foundation for advancing this promising direction in LLM reasoning. The relevant papers will be regularly updated at https://github.com/EIT-NLP/Awesome-Latent-CoT.
Sources
- Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
- Soft Tokens, Hard Truths
- Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
- Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
- SEAL: Steerable Reasoning Calibration of Large Language Models for Free
- Reasoning Models Don't Always Say What They Think
- Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
- Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Do Language Models Use Their Depth Efficiently?
- LLM Latent Reasoning as Chain of Superposition
- SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- Learning to Ponder: Adaptive Reasoning in Latent Space
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
- Efficient Reasoning Models: A Survey
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Thinking Tokens for Language Modeling
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering