# LLM Latent Reasoning as Chain of Superposition

arXiv: https://arxiv.org/abs/2510.15522 · HTML: https://mlsanity.com/paper/2510.15522/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step](https://mlsanity.com/paper/2405.14838/) (2024)
- [CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation](https://mlsanity.com/paper/2502.21074/) (2025)
- [Compressed Chain of Thought: Efficient Reasoning Through Dense Representations](https://mlsanity.com/paper/2412.13171/) (2024)
- [Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space](https://mlsanity.com/paper/2505.15778/) (2025)
- [Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains](https://mlsanity.com/paper/2505.16552/) (2025)
- [A Survey on Latent Reasoning](https://mlsanity.com/paper/2507.06203/) (2025)
- [LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking](https://mlsanity.com/paper/2508.03440/) (2025)
- [Parallel Continuous Chain-of-Thought with Jacobi Iteration](https://mlsanity.com/paper/2506.18582/) (2025)
- [Text Generation Beyond Discrete Token Sampling](https://mlsanity.com/paper/2505.14827/) (2025)
- [Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment](https://mlsanity.com/paper/2502.11401/) (2025)
- [RLKD: Distilling LLMs' Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2505.16142/) (2025)
- [Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks](https://mlsanity.com/paper/2507.17747/) (2025)
- [Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks](https://mlsanity.com/paper/2508.20038/) (2025)

## Built on by (most cited first, 30 of 39)

- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space](https://mlsanity.com/paper/2512.12623/) (2025)
- [SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization](https://mlsanity.com/paper/2511.06411/) (2025)
- [Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning](https://mlsanity.com/paper/2601.14750/) (2026)
- [Solve the Loop: Attractor Models for Language and Reasoning](https://mlsanity.com/paper/2605.12466/) (2026)
- [Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers](https://mlsanity.com/paper/2606.31779/) (2026)
- [Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning](https://mlsanity.com/paper/2604.27998/) (2026)
- [Are Latent Reasoning Models Easily Interpretable?](https://mlsanity.com/paper/2604.04902/) (2026)
- [Latent On-Policy Self-Distillation](https://mlsanity.com/paper/2608.13040/) (2026)
- [Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning](https://mlsanity.com/paper/2605.07106/) (2026)
- [Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models](https://mlsanity.com/paper/2601.05693/) (2026)
- [SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models](https://mlsanity.com/paper/2603.06222/) (2026)
- [Latent Reasoning with Normalizing Flows](https://mlsanity.com/paper/2606.06447/) (2026)
- [When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning](https://mlsanity.com/paper/2603.03475/) (2026)
- [Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus](https://mlsanity.com/paper/2604.03809/) (2026)
- [Semantic-Enriched Latent Visual Reasoning](https://mlsanity.com/paper/2605.19342/) (2026)
- [Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention](https://mlsanity.com/paper/2606.01243/) (2026)
- [What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis](https://mlsanity.com/paper/2606.20075/) (2026)
- [Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning](https://mlsanity.com/paper/2606.13106/) (2026)
- [Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression](https://mlsanity.com/paper/2606.29712/) (2026)
- [MUX: Continuous Reasoning via Multiplexed Tokens](https://mlsanity.com/paper/2607.18264/) (2026)
- [The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA](https://mlsanity.com/paper/2609.03090/) (2026)
- [LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification](https://mlsanity.com/paper/2605.07315/) (2026)
- [Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs](https://mlsanity.com/paper/2606.27378/) (2026)
- [Structural Process Supervision for Latent Chain-of-Thought Reasoning](https://mlsanity.com/paper/2609.09928/) (2026)
- [AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models](https://mlsanity.com/paper/2610.01560/) (2026)
- [LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG](https://mlsanity.com/paper/2605.06285/) (2026)
- [Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning](https://mlsanity.com/paper/2606.10184/) (2026)
- [SuperThoughts: Reasoning Tokens in Superposition](https://mlsanity.com/paper/2606.13862/) (2026)
- [LatentMT: Machine Translation with Latent Reasoning](https://mlsanity.com/paper/2607.18618/) (2026)

## Abstract (arXiv)

Latent reasoning offers a computation-efficient alternative to Chain-of-Thought but often suffers from performance degradation due to distributional misalignment and ambiguous chain definitions. Ideally, latent reasoning should function as a superposition of multiple reasoning paths. To realize this, we introduce Latent-SFT, a unified framework addressing challenges at three levels: token, chain, and learning. First, we define the Latent-Vocab to constrain hidden states within the pre-trained vocab-space. Second, we construct the Latent-Chain via Induction-Supervision Masking to ensure semantic compactness and sufficiency. Third, we employ Latent-Optim with stochastic Gumbel-Softmax to guide the model toward generalizable solutions. Empirical results demonstrate that Latent-SFT consistently outperforms explicit SFT across six mathematical benchmarks (e.g., GSM8k, AIME24) while achieving a 2.7x to 5.5x reduction in reasoning length. Analysis confirms that our method effectively captures a superposition of diverse reasoning trajectories rather than merely compressing a single path.