cs.LGNov 18, 2026

Rethinking Fixed-Horizon Latent Reasoning

Authors: Tianxiang Chen, Jingyuan Zhou, Weiming Yang, Kaidi Yang

Organizations: Department of Civil and Environmental Engineering, National University of Singapore

Abstract

Existing latent reasoners typically run for a preset latent horizon during inference. Intuitively, a longer horizon should provide more opportunity for reasoning. However, in this work, we find that extending latent Chain-of-Thought (CoT) to the full preset horizon may in fact degrade reasoning performance. We observe that latent CoT evolves through distinct functional stages, with earlier computation forming frontier reasoning states, while later computation mainly reorganizes existing candidates and can weaken gold candidate support. These findings motivate a rethink of fixed-horizon latent inference. To address this, we characterize the reasoning benefits of latent CoT by realized and remaining constructive progress. Empirically, we find that higher realized constructive progress corresponds to higher current reasoning accuracy, while more remaining progress corresponds to larger future gains from continued latent CoT. To this end, we introduce a lightweight method that estimates the remaining reasoning progress and adaptively adjusts the latent horizon during inference. Across representative latent CoT reasoners and multiple arithmetic benchmarks, our method improves reasoning accuracy by up to 7.2 percentage points while reducing latent computation by up to 29.0%, without retraining the LLM.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains

    May 25, 2026Hui Xie, Jie Liu, Ziyue Qiao +1Efficient Language Model ReasoningLLM Inference Acceleration

  2. Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate

    Jun 15, 2026Hanyu Lin, Min Cai, Jiawei Wen +1Latent ReasoningLLM Reasoning

  3. From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers

    Oct 8, 2026Gerard Grau García, Arnau Padrés Masdemont, Niccolò Grillo +3Efficient Language Model ReasoningContinuous Latent Reasoning