Latent CoT Reasoning

CoT: Chain-of-Thought

Overview

Latent chain-of-thought reasoning asks whether language models can perform multi-step computation in hidden states or compact learned tokens, potentially reducing the cost of generating long verbal explanations. Approaches include recurrent hidden-state reasoning, discrete or continuous latent tokens, and methods that compress or selectively retain explicit steps; training uses distillation, process supervision, reinforcement learning, and alignment with written reasoning traces. Work spans math and symbolic benchmarks as well as multimodal, structured-data, and tool-using tasks, with methods increasingly combining latent exploration with explicit verification. A central open question is whether latent states genuinely guide answers and remain monitorable, rather than merely correlating with success, while preserving the accuracy and flexibility of explicit chain-of-thought.

Latest papers

CardsList

31 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning

    May 22, 2025Xinghao Chen, Anhao Zhao, Heming Xia +7CoT ReasoningLLM Reasoning