# LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

arXiv: https://arxiv.org/abs/2602.07075 · HTML: https://mlsanity.com/paper/2602.07075/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 41 of its 65 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 30 of 41)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step](https://mlsanity.com/paper/2405.14838/) (2024)
- [Compressed Chain of Thought: Efficient Reasoning Through Dense Representations](https://mlsanity.com/paper/2412.13171/) (2024)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models](https://mlsanity.com/paper/2306.08018/) (2023)
- [MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter](https://mlsanity.com/paper/2310.12798/) (2023)
- [MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency](https://mlsanity.com/paper/2502.09621/) (2025)
- [SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs](https://mlsanity.com/paper/2502.12134/) (2025)
- [ChemLLM: A Chemical Large Language Model](https://mlsanity.com/paper/2402.06852/) (2024)
- [ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area](https://mlsanity.com/paper/2408.07246/) (2024)
- [SIM-CoT: Supervised Implicit Chain-of-Thought](https://mlsanity.com/paper/2509.20317/) (2025)
- [Training a Scientific Reasoning Model for Chemistry](https://mlsanity.com/paper/2506.17238/) (2025)
- [Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding](https://mlsanity.com/paper/2411.04282/) (2024)
- [Developing ChemDFM as a large language foundation model for chemistry](https://mlsanity.com/paper/2401.14818/) (2024)
- [Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations](https://mlsanity.com/paper/2505.21318/) (2025)
- [ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning](https://mlsanity.com/paper/2501.06590/) (2025)
- [SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning](https://mlsanity.com/paper/2505.11484/) (2025)
- [ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute](https://mlsanity.com/paper/2509.04475/) (2025)
- [Nature Language Model: Deciphering the Language of Nature for Scientific Discovery](https://mlsanity.com/paper/2502.07527/) (2025)
- [Deliberation in Latent Space via Differentiable Cache Augmentation](https://mlsanity.com/paper/2412.17747/) (2024)
- [Parallel Continuous Chain-of-Thought with Jacobi Iteration](https://mlsanity.com/paper/2506.18582/) (2025)
- [ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge](https://mlsanity.com/paper/2507.21990/) (2025)
- [Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey](https://mlsanity.com/paper/2403.01528/) (2024)
- [ChemMLLM: Chemical Multimodal Large Language Model](https://mlsanity.com/paper/2505.16326/) (2025)
- [Chem-R: Learning to Reason as a Chemist](https://mlsanity.com/paper/2510.16880/) (2025)
- [Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought](https://mlsanity.com/paper/2509.23365/) (2025)

## Built on by (most cited first, 8 of 8)

- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails](https://mlsanity.com/paper/2605.17329/) (2026)
- [MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback](https://mlsanity.com/paper/2606.12916/) (2026)
- [Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs](https://mlsanity.com/paper/2606.27378/) (2026)
- [FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization](https://mlsanity.com/paper/2605.10230/) (2026)
- [Localize, Then Reason: Visual Latent Structural Reasoning for Molecular Properties and Edits](https://mlsanity.com/paper/2608.13244/) (2026)
- [Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry](https://mlsanity.com/paper/2610.01947/) (2026)
- [Hybrid Reasoning Agents](https://mlsanity.com/paper/2610.18861/) (2026)

## Abstract (arXiv)

Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex reasoning problems. However, forcing nonverbal tacit chemical logic into discrete natural language imposes a fundamental ``modality mismatch,'' creating an artificial bottleneck for reasoning. We introduce LatentChem, a reasoning interface that decouples chemical logic from linguistic generation, enabling the model to process information via continuous thought vectors and dynamic perception. Our investigation reveals a pivotal emergent behavior: spontaneous internalization, defined here as self-selected under outcome-only optimization. When optimized for task success, the model abandons verbose textual derivations in favor of implicit latent computation, suggesting that it identifies the continuous manifold as a more native substrate for chemical logic. This paradigm shift also proves to be a superior computational strategy: LatentChem achieves a 59.88% non-tie win rate against the strong CoT baseline on the rigorous ChemCoTBench, while delivering a broad 10.84× average reduction in reasoning step overhead (5.96× wall-clock speedup) across all evaluated benchmarks. Our results provide empirical evidence that chemical reasoning is more naturally and effectively realized as continuous latent dynamics rather than discretized linguistic trajectories.