Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning

• URL: http://arxiv.org/abs/2511.21581v1
• Date: Wed, 26 Nov 2025 16:54:06 GMT
• Title: Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning
• Authors: Alex Ning, Yen-Ling Kuo, Gabe Gomes,
• Abstract summary: We develop adaptive-length latent reasoning models and introduce a post-SFT reinforcement-learning methodology.<n> Experiments on the Llama 3.2 1B model and the GSM8K-Aug dataset show a $52%$ drop in total reasoning length with no penalty to accuracy.
• Score: 7.669927190506031
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent state into the next sequence, latent reasoning removes the restriction to human language tokens as the medium for reasoning. We develop adaptive-length latent reasoning models and introduce a post-SFT reinforcement-learning methodology to optimize latent reasoning length by minimizing reasoning length while maintaining accuracy. This, in turn, further reduces compute usage and raises the bar on the compressive capabilities of latent reasoning models. Experiments on the Llama 3.2 1B model and the GSM8K-Aug dataset show a $52\%$ drop in total reasoning length with no penalty to accuracy. In future work, we plan to extend to additional models and datasets, analyze relationships between training coefficients, experiment with architecture variations, and continue our knowledge distillation for latent reasoning SFT efforts. We make our code and pretrained weights available at https://github.com/apning/adaptive-latent-reasoning.

Related papers

• CoLT: Reasoning with Chain of Latent Tool Calls [31.228763375347608]
  Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs)<n>We propose CoLT, a novel framework that implements latent reasoning as tool calls''
  arXiv  Detail & Related papers  (2026-02-04T06:12:53Z)
• ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought [49.203970812338916]
  Explicit reasoning chains introduce substantial computational redundancy.<n>Recent latent reasoning methods attempt to mitigate this by compressing reasoning processes into latent space.<n>We propose Rendered CoT-Guided variational Latent Reasoning (ReGuLaR)
  arXiv  Detail & Related papers  (2026-01-30T17:08:06Z)
• Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization [9.193078163792427]
  Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems.<n>Recent latent reasoning approaches attempt to optimize efficiency by performing reasoning within continuous hidden states.<n>We introduce PLaT, a framework that reformulates latent reasoning as planning by fundamentally decouple reasoning from verbalization.
  arXiv  Detail & Related papers  (2026-01-29T07:38:18Z)
• Structured Reasoning for Large Language Models [59.215789462977206]
  We propose Structured Reasoning (SCR), a framework that decouples reasoning trajectories into explicit, evaluable, and trainable components.<n>SCR substantially improves reasoning efficiency and self-verification.<n>Compared with existing reasoning paradigms, it reduces output token length by up to 50%.
  arXiv  Detail & Related papers  (2026-01-12T04:04:01Z)
• Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking [50.97239453902612]
  Large Reasoning Models (LRMs) have achieved impressive performance on challenging tasks, yet their deep reasoning often incurs substantial computational costs.<n>Inspired by Evidence Accumulation Models, we find that LRMs have accumulated sufficient information early in reasoning, making further reasoning steps redundant.<n>We propose Just-Enough Thinking (JET), which trains models to proactively terminate unnecessary reasoning.
  arXiv  Detail & Related papers  (2025-09-27T16:25:06Z)
• Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors [45.578570554635775]
  Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought.<n>We study a simple mechanism that converts recurring reasoning fragments into concise, reusable "behaviors"<n>These behaviors are stored in a "behavior handbook" which supplies them to the model in-context at inference or distills them into parameters via supervised fine-tuning.
  arXiv  Detail & Related papers  (2025-09-16T16:44:26Z)
• CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models [29.95434387343843]
  We propose a unified framework that mitigates length bias through three components.<n>CoLD consistently reduces reward-length correlation, improves accuracy in step selection, and encourages more concise, logically valid reasoning.
  arXiv  Detail & Related papers  (2025-07-21T15:07:59Z)
• TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression [55.37723860832064]
  We propose a dynamic ratio-based training pipeline that does not rely on sophisticated data annotations.<n>We validate our approach across models on DeepSeek-R1-Distill-7B and DeepSeek-R1-Distill-14B and on a diverse set of benchmarks with varying difficulty levels.
  arXiv  Detail & Related papers  (2025-06-03T09:23:41Z)
• Interleaved Reasoning for Large Language Models via Reinforcement Learning [22.403928213802036]
  Long chain-of-thought (CoT) enhances large language models' (LLM) reasoning capabilities.<n>We propose a novel training paradigm that uses reinforcement learning (RL) to guide reasoning LLMs to interleave thinking and answering for multi-hop questions.
  arXiv  Detail & Related papers  (2025-05-26T07:58:17Z)
• Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards [17.829990749622496]
  We propose an adaptive reward-shaping method for large language models.<n>Our method dynamically adjusts the trade-off between accuracy and response length based on model performance.<n> Experiments show that our approach consistently and dramatically reduces reasoning length while largely maintaining accuracy.
  arXiv  Detail & Related papers  (2025-05-23T18:44:46Z)
• Do Larger Language Models Generalize Better? A Scaling Law for Implicit Reasoning at Pretraining Time [73.22651918134808]
  This work shows counterintuitive effects of model size scaling and provides new insights into the relationship between scaling and reasoning in language models (LMs)<n>We pretrain LMs from scratch on a synthetic implicit multihop reasoning environment designed to replicate the structure and distribution of real-world large-scale knowledge graphs.<n>We then assess the LMs' ability to complete the missing edges in the graph, which requires multi-hop reasoning that can be viewed as a simplification of implicit reasoning during real-world pretraining.
  arXiv  Detail & Related papers  (2025-04-04T17:57:22Z)
• Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning [108.07030347318624]
  We show that scaling with longer Chain of Thoughts (CoTs) can indeed impair the reasoning performance of Large Language Models (LLMs) in certain domains.<n>We propose a Thinking- Optimal Scaling strategy to teach models to adopt different reasoning efforts for deep thinking.<n>Our self-improvement models built upon Qwen2.5-32B-Instruct outperform other distillation-based 32B o1-like models across various math benchmarks.
  arXiv  Detail & Related papers  (2025-02-25T10:48:05Z)
• Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
  Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
  arXiv  Detail & Related papers  (2024-10-21T17:00:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.