# SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought

arXiv: https://arxiv.org/abs/2508.00574 · HTML: https://mlsanity.com/paper/2508.00574/

## Key facts

- Cited by 14 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 42 of its 54 references that are in the map.
- First posted on arXiv 1 Aug 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 42)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning](https://mlsanity.com/paper/2504.11456/) (2025)
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (2025)
- [Think before you speak: Training Language Models With Pause Tokens](https://mlsanity.com/paper/2310.02226/) (2023)
- [Chain of Thought Empowers Transformers to Solve Inherently Serial Problems](https://mlsanity.com/paper/2402.12875/) (2024)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [Training Language Models to Reason Efficiently](https://mlsanity.com/paper/2502.04463/) (2025)
- [Reasoning with Latent Thoughts: On the Power of Looped Transformers](https://mlsanity.com/paper/2502.17416/) (2025)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (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)
- [Let's Think Dot by Dot: Hidden Computation in Transformer Language Models](https://mlsanity.com/paper/2404.15758/) (2024)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [CoT-Valve: Length-Compressible Chain-of-Thought Tuning](https://mlsanity.com/paper/2502.09601/) (2025)

## Built on by (most cited first, 14 of 14)

- [Monet: Reasoning in Latent Visual Space Beyond Images and Language](https://mlsanity.com/paper/2511.21395/) (2025)
- [Implicit Reasoning in Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.02350/) (2025)
- [SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization](https://mlsanity.com/paper/2511.06411/) (2025)
- [LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning](https://mlsanity.com/paper/2602.07075/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Beyond Imitation: Reinforcement Learning for Active Latent Planning](https://mlsanity.com/paper/2601.21598/) (2026)
- [Capabilities and Fundamental Limits of Latent Chain-of-Thought](https://mlsanity.com/paper/2602.01148/) (2026)
- [Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model](https://mlsanity.com/paper/2605.12163/) (2026)
- [ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model](https://mlsanity.com/paper/2601.22730/) (2026)
- [Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning](https://mlsanity.com/paper/2607.00461/) (2026)
- [LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG](https://mlsanity.com/paper/2605.06285/) (2026)
- [RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step](https://mlsanity.com/paper/2605.09346/) (2026)
- [N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization](https://mlsanity.com/paper/2606.10768/) (2026)
- [Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought Reasoning](https://mlsanity.com/paper/2609.07406/) (2026)

## Abstract (arXiv)

While Chain-of-Thought (CoT) reasoning improves model performance, it incurs significant time costs due to the generation of discrete CoT tokens (DCoT). Continuous CoT (CCoT) offers a more efficient alternative, but existing CCoT methods are hampered by indirect fine-tuning, limited alignment, or inconsistent targets. To overcome these limitations, we propose textitSynAdapt, an innovative efficient reasoning framework. Specifically, textitSynAdapt generates the synthetic CCoT to serve as a precise and effective alignment target for LLMs. This synthetic CCoT explicitly guides the LLM to learn CCoT and derive accurate answers directly. Furthermore, relying solely on CCoT is insufficient for solving hard questions. To address this, textitSynAdapt integrates a difficulty classifier that leverages both question context and CCoT to identify hard questions. CCoT can effectively help identify hard questions after some brief reasoning. We then adaptively prompt the LLM to re-think these hard questions for improved performance. Extensive experimental results across various benchmarks from different difficulty levels strongly demonstrate the effectiveness of our method, achieving the best accuracy-efficiency trade-off.