J-CoT: Chain-of-Thought in J-Space

• URL: http://arxiv.org/abs/2607.21981v1
• Date: Fri, 24 Jul 2026 04:57:30 GMT
• Title: J-CoT: Chain-of-Thought in J-Space
• Abstract summary: Chain-of-thought prompting improves language-model reasoning by carrying intermediate states across successive computation steps.<n>We introduce textbfJ-CoT, a recurrent reasoning framework built on emphJ-space, a vocabulary-indexed coordinate system within the model's hidden representations.
• Score: 7.893457716552934
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chain-of-thought prompting improves language-model reasoning by carrying intermediate states across successive computation steps. However, relying on natural language as the only recurrent interface is overly restrictive, since many transient computations do not need to be fully verbalized. Existing latent-reasoning methods remove this constraint by recurrently propagating continuous hidden states. However, these methods pass a dense hidden vector as a whole, without an explicit mechanism for selecting and organizing the information needed by the next reasoning step. This motivates an intermediate interface that remains linguistically grounded without requiring a decoded sentence. We introduce \textbf{J-CoT}, a recurrent reasoning framework built on \emph{J-space}, a vocabulary-indexed coordinate system within the model's hidden representations. Within each cycle, the model computes in its full hidden space. At the cycle boundary, J-CoT expresses the intermediate state as vocabulary-indexed coefficients, carries these coefficients forward as a \emph{J-thought}, and maps them back into the model's hidden representation for the next cycle. J-CoT therefore requires neither a fluent intermediate rationale nor recurrence over the complete hidden state. Under matched backbone and inference settings, J-CoT-Zero matches or exceeds the strongest evaluated latent-reasoning baseline on every benchmark, while J-CoT-Train obtains the highest score across the evaluated mathematical, scientific, coding, and structured path-reasoning tasks.

Related papers

• Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate [3.794106972075877]
  Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens.<n>Latent reasoning offers a promising alternative by carrying part of the computation in continuous representations.<n>We propose textbfTyped textbfent textbfReasoning (Tyler), a typed and budget-aware framework for latent reasoning during autoregressive decoding.
  arXiv  Detail & Related papers  (2026-06-15T07:56:05Z)
• Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics [49.443264461057645]
  Diffusion and continuous flow-based language models have emerged as the leading non-autoregressive alternatives to language modeling.<n>Progress in both paradigms is overwhelmingly tracked by generative perplexity (gen-PPL): the per-token negative log-likelihood of samples under a frozen autoregressive (AR) scorer.<n>We argue that this metric is unsound. By construction, gen-PPL measures only predictability under the scoring AR, not grammaticality or semantic coherence.
  arXiv  Detail & Related papers  (2026-06-07T02:35:56Z)
• Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought [13.72996269125319]
  Abstract-CoT achieves up to $11.6times$ fewer reasoning tokens while demonstrating comparable performance across mathematical reasoning, instruction-following, and multi-hop reasoning.<n>Our findings highlight the potential for post-training latent reasoning mechanisms that enable efficient inference through a learned abstract reasoning language.
  arXiv  Detail & Related papers  (2026-04-24T16:45:51Z)
• SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models [15.95627037350657]
  Explicit Chain-of-Thought (CoT) computation incurs high inference cost due to internalize token-level traces.<n>We propose SPOT, a flexible framework that compresses explicit CoT into compact latent pause tokens without enforcing a fixed response template.<n>Experiments on reasoning benchmarks demonstrate that SPOT improves accuracy by 2.3 points on average while reducing generated tokens by 37.5%.
  arXiv  Detail & Related papers  (2026-03-06T12:34:27Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• SIM-CoT: Supervised Implicit Chain-of-Thought [108.30049193668083]
  Implicit Chain-of-Thought (CoT) methods offer a token-efficient alternative to explicit CoT reasoning in Large Language Models.<n>We identify a core latent instability issue when scaling the computational budget of implicit CoT.<n>We propose SIM-CoT, a plug-and-play training module that introduces step-level supervision to stabilize and enrich the latent reasoning space.
  arXiv  Detail & Related papers  (2025-09-24T17:01:32Z)
• Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer [0.8738725605667471]
  Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning.<n>In standard decoder-only architectures, these reasoning steps are externalized in natural language, improving interpretability at the cost of efficiency.<n>We investigate whether such reasoning structures emerge in Huginn-3.5B, a depth-recurrent Transformer that reuses layers at inference time without increasing parameter count.
  arXiv  Detail & Related papers  (2025-07-02T23:35:21Z)
• Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling [90.86991492288487]
  evaluating constraint on every token can be prohibitively expensive.<n> LCD can distort the global distribution over strings, sampling tokens based only on local information.<n>We show that our approach is superior to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-04-07T18:30:18Z)
• CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation [30.762815456866083]
  We introduce CODI (Continuous Chain-of-Thought via Self-Distillation), a novel training framework that effectively compresses natural language CoT into continuous space.<n>Experiments show CODI is the first implicit CoT approach to match the performance of explicit CoT on GSM8k at the GPT-2 scale.
  arXiv  Detail & Related papers  (2025-02-28T14:07:48Z)
• Training Large Language Models to Reason in a Continuous Latent Space [71.0274000348354]
  We introduce a new paradigm called Coconut (Chain of Continuous Thought) to explore the potential of reasoning beyond language.<n>Instead of decoding this state into words, we feed it back to the model as the next input embedding directly in the continuous space.<n>This latent reasoning paradigm enables an advanced reasoning pattern, where continuous thoughts can encode multiple alternative next steps.
  arXiv  Detail & Related papers  (2024-12-09T18:55:56Z)
• Spatial Semantic Recurrent Mining for Referring Image Segmentation [63.34997546393106]
  We propose Stextsuperscript2RM to achieve high-quality cross-modality fusion. It follows a working strategy of trilogy: distributing language feature, spatial semantic recurrent coparsing, and parsed-semantic balancing. Our proposed method performs favorably against other state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-05-15T00:17:48Z)

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.