# SIM-CoT: Supervised Implicit Chain-of-Thought

arXiv: https://arxiv.org/abs/2509.20317 · HTML: https://mlsanity.com/paper/2509.20317/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 51 of its 54 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 30 of 51)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)
- [Reasoning with Latent Thoughts: On the Power of Looped Transformers](https://mlsanity.com/paper/2502.17416/) (2025)
- [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)
- [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023)
- [Progressive-Hint Prompting Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2304.09797/) (2023)

## Built on by (most cited first, 30 of 70)

- [Monet: Reasoning in Latent Visual Space Beyond Images and Language](https://mlsanity.com/paper/2511.21395/) (2025)
- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving](https://mlsanity.com/paper/2603.01928/) (2026)
- [Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models](https://mlsanity.com/paper/2602.01166/) (2026)
- [SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization](https://mlsanity.com/paper/2511.06411/) (2025)
- [Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models](https://mlsanity.com/paper/2605.26733/) (2026)
- [DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2603.22280/) (2026)
- [Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning](https://mlsanity.com/paper/2605.21488/) (2026)
- [LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning](https://mlsanity.com/paper/2601.10129/) (2026)
- [ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning](https://mlsanity.com/paper/2512.05111/) (2025)
- [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)
- [STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence](https://mlsanity.com/paper/2510.24693/) (2025)
- [Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure](https://mlsanity.com/paper/2602.08783/) (2026)
- [Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation](https://mlsanity.com/paper/2604.18486/) (2026)
- [Deep Thinking by Markov Chain of Continuous Thoughts](https://mlsanity.com/paper/2509.25020/) (2025)
- [Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI](https://mlsanity.com/paper/2510.16720/) (2025)
- [LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning](https://mlsanity.com/paper/2602.07075/) (2026)
- [ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces](https://mlsanity.com/paper/2602.11683/) (2026)
- [HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization](https://mlsanity.com/paper/2604.20328/) (2026)
- [Chain Of Thought Compression: A Theoretical Analysis](https://mlsanity.com/paper/2601.21576/) (2026)
- [OneLatent: Single-Token Compression for Visual Latent Reasoning](https://mlsanity.com/paper/2602.13738/) (2026)
- [Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing](https://mlsanity.com/paper/2602.16455/) (2026)
- [LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck](https://mlsanity.com/paper/2606.13061/) (2026)
- [Pretraining with Token-Level Adaptive Latent Chain-of-Thought](https://mlsanity.com/paper/2602.08220/) (2026)
- [Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens](https://mlsanity.com/paper/2602.10229/) (2026)
- [Visual Enhanced Depth Scaling for Multimodal Latent Reasoning](https://mlsanity.com/paper/2604.10500/) (2026)
- [Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model](https://mlsanity.com/paper/2605.12163/) (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)

## Abstract (arXiv)

Implicit Chain-of-Thought (CoT) methods offer a token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited their adoption. We identify a core latent instability issue when scaling the computational budget of implicit CoT: as the number of reasoning tokens increases, training often becomes unstable and collapses. Our analysis shows that this instability arises from latent representations becoming homogeneous and losing semantic diversity, caused by insufficient step-level supervision in current implicit CoT methods. To address this, we propose SIM-CoT, a plug-and-play training module that introduces step-level supervision to stabilize and enrich the latent reasoning space. SIM-CoT employs an auxiliary decoder during training to align each implicit token with its corresponding explicit reasoning step, ensuring latent states capture distinct and meaningful information. The auxiliary decoder is removed at inference, preserving the efficiency of implicit CoT with no added overhead. It also provides interpretability by projecting each latent token onto an explicit reasoning vocabulary, enabling per-step visualization and diagnosis. SIM-CoT significantly improves both in-domain accuracy and out-of-domain stability of implicit CoT methods, boosting Coconut by +8.2% on GPT-2 and CODI by +3.0% on LLaMA-3.1 8B. It further surpasses the explicit CoT baseline on GPT-2 by 2.1% with 2.3× greater token efficiency, while closing the performance gap on larger models like LLaMA-3.1 8B. Code: https://github.com/InternLM/SIM-CoT