pith. sign in

arxiv: 2507.06203 · v2 · pith:755WHYYQnew · submitted 2025-07-08 · 💻 cs.CL

A Survey on Latent Reasoning

classification 💻 cs.CL
keywords reasoninglatentexplicitgithubhiddenlanguagemodelmodels
0
0 comments X
read the original abstract

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate steps. While CoT improves both interpretability and accuracy, its dependence on natural language reasoning limits the model's expressive bandwidth. Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state, eliminating token-level supervision. To advance latent reasoning research, this survey provides a comprehensive overview of the emerging field of latent reasoning. We begin by examining the foundational role of neural network layers as the computational substrate for reasoning, highlighting how hierarchical representations support complex transformations. Next, we explore diverse latent reasoning methodologies, including activation-based recurrence, hidden state propagation, and fine-tuning strategies that compress or internalize explicit reasoning traces. Finally, we discuss advanced paradigms such as infinite-depth latent reasoning via masked diffusion models, which enable globally consistent and reversible reasoning processes. By unifying these perspectives, we aim to clarify the conceptual landscape of latent reasoning and chart future directions for research at the frontier of LLM cognition. An associated GitHub repository collecting the latest papers and repos is available at: https://github.com/multimodal-art-projection/LatentCoT-Horizon/.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning

    cs.CL 2026-05 unverdicted novelty 7.0

    CopT reverses CoT by eliciting a draft answer first then using continuous-embedding contrastive verification and on-policy thinking to reflect and correct, yielding up to 23% higher accuracy and 57% fewer tokens witho...

  2. LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models

    cs.LG 2026-05 unverdicted novelty 7.0

    LoopUS converts pretrained LLMs into looped latent refinement models via block decomposition, selective gating, random deep supervision, and confidence-based early exiting to improve reasoning performance.

  3. LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification

    cs.CL 2026-05 unverdicted novelty 7.0

    LaTER reduces LLM token usage 16-33% on reasoning benchmarks by exploring in latent space then switching to explicit CoT verification, with gains like 70% to 73.3% on AIME 2025 in the training-free version.

  4. LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG

    cs.CL 2026-05 unverdicted novelty 7.0

    LatentRAG performs agentic RAG by generating latent tokens for thoughts and subqueries in one forward pass, matching explicit methods' accuracy on seven benchmarks while reducing latency by ~90%.

  5. SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving

    cs.CL 2025-11 unverdicted novelty 7.0

    SpiralThinker stabilizes iterative latent reasoning in LLMs via text-latent interleaving and progressive alignment, achieving SOTA results among latent baselines on math, logic, and commonsense tasks.

  6. Scaling Latent Reasoning via Looped Language Models

    cs.CL 2025-10 unverdicted novelty 7.0

    Looped language models with latent iterative computation and entropy-regularized depth allocation achieve performance matching up to 12B standard LLMs through superior knowledge manipulation.

  7. Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

    cs.LG 2026-06 unverdicted novelty 6.0

    LOTUS uses a looped padded Transformer with parallel cross-entropy supervision on gold CoT tokens to match explicit CoT performance at 3B parameters while reducing thought-phase latency 2.5x-6.9x.

  8. Intuition-Guided Latent Reasoning for LLM-Based Recommendation

    cs.IR 2026-06 unverdicted novelty 6.0

    IntuRec anchors LLM latent reasoning for recommendation by deriving an intuition embedding from top-K candidates via self- and cross-attention to initialize more accurate trajectories.

  9. LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck

    cs.CV 2026-06 unverdicted novelty 6.0

    LaME performs latent multimodal embedding reasoning with K learnable reason tokens in a weakly supervised information bottleneck, matching some explicit CoT models while running 60x faster.

  10. Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models

    cs.AI 2026-06 unverdicted novelty 6.0

    No-CoT 50% task-completion time horizons for frontier models have doubled yearly for six years, reaching over 3 minutes for GPT-5.5, with median projections of 7 minutes by 2028 and 25 minutes by 2030.

  11. LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?

    cs.AI 2026-05 unverdicted novelty 6.0

    LatentRouter routes image-question queries to the best MLLM by predicting counterfactual performance via latent communication between learned query capsules and model capability tokens.

  12. HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering

    cs.AI 2026-04 unverdicted novelty 6.0

    HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.

  13. PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models

    cs.CL 2026-01 unverdicted novelty 6.0

    PILOT internalizes strategic planning into compact LLMs by using a hyper-network to generate query-conditioned latent guidance vectors that stabilize reasoning trajectories and improve benchmark performance with negli...

  14. Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

    cs.LG 2026-06 unverdicted novelty 5.0

    Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.

  15. Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models

    cs.AI 2026-06 unverdicted novelty 5.0

    Frontier AI models' no-CoT 50% task-completion time horizons have doubled yearly over six years, reaching over 3 minutes for GPT-5.5 with projections to 25 minutes by 2030.

  16. Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models

    cs.LG 2026-05 unverdicted novelty 5.0

    STARS trains looped language models with Jacobian spectral radius regularization and random loop sampling to drive latent states toward asymptotically stable fixed points, yielding reliable test-time scaling on arithm...

  17. LLM Reasoning Is Latent, Not the Chain of Thought

    cs.AI 2026-04 unverdicted novelty 5.0

    LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.

  18. Latent-CURE for Breast Cancer Diagnosis

    cs.CV 2026-06 unverdicted novelty 4.0

    Latent-CURE introduces latent-space chain-of-thought reasoning and dual-asymmetric optimization to produce transparent, robust breast cancer diagnoses in imbalanced cohorts.

  19. Measuring AI Reasoning: A Guide for Researchers

    cs.AI 2026-05 unverdicted novelty 4.0

    Reasoning in language models should be measured by the faithfulness and validity of their multi-step search processes and intermediate traces, not final-answer accuracy.