# StreamingThinker: Large Language Models Can Think While Reading

arXiv: https://arxiv.org/abs/2510.17238 · HTML: https://mlsanity.com/paper/2510.17238/

## Key facts

- Cited by 15 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 36 of its 57 references that are in the map.
- First posted on arXiv 20 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, 30 of 36)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language](https://mlsanity.com/paper/2012.13048/) (2020)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Reward-Guided Speculative Decoding for Efficient LLM Reasoning](https://mlsanity.com/paper/2501.19324/) (2025)
- [LightThinker: Thinking Step-by-Step Compression](https://mlsanity.com/paper/2502.15589/) (2025)
- [Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models](https://mlsanity.com/paper/2504.04823/) (2025)
- [Effectively Controlling Reasoning Models through Thinking Intervention](https://mlsanity.com/paper/2503.24370/) (2025)
- [Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?](https://mlsanity.com/paper/2504.06514/) (2025)
- [Learning Adaptive Parallel Reasoning with Language Models](https://mlsanity.com/paper/2504.15466/) (2025)
- [Towards Reasoning Ability of Small Language Models](https://mlsanity.com/paper/2502.11569/) (2025)
- [STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models](https://mlsanity.com/paper/2507.15375/) (2025)
- [Interleaved Reasoning for Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2505.19640/) (2025)
- [Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models](https://mlsanity.com/paper/2508.15827/) (2025)
- [Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models](https://mlsanity.com/paper/2408.05093/) (2024)
- [Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation](https://mlsanity.com/paper/2405.10443/) (2024)
- [Decoder-only Streaming Transformer for Simultaneous Translation](https://mlsanity.com/paper/2406.03878/) (2024)

## Built on by (most cited first, 15 of 15)

- [Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously](https://mlsanity.com/paper/2603.12262/) (2026)
- [HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit](https://mlsanity.com/paper/2602.23699/) (2026)
- [Thinking in Streaming Video](https://mlsanity.com/paper/2603.12938/) (2026)
- [Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models](https://mlsanity.com/paper/2601.06843/) (2026)
- [Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2603.11896/) (2026)
- [Asynchronous Reasoning: Training-Free Interactive Thinking LLMs](https://mlsanity.com/paper/2512.10931/) (2025)
- [Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2603.02872/) (2026)
- [When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning](https://mlsanity.com/paper/2605.03314/) (2026)
- [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026)
- [Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs](https://mlsanity.com/paper/2605.12460/) (2026)
- [Learning When to Think While Listening in Large Audio-Language Models](https://mlsanity.com/paper/2605.27190/) (2026)
- [Never Stop Thinking: Continuous-Time Language Agents](https://mlsanity.com/paper/2609.17416/) (2026)
- [ProactiveLLM: Learning Active Interaction for Streaming Large Language Models](https://mlsanity.com/paper/2606.00523/) (2026)
- [AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization](https://mlsanity.com/paper/2606.14694/) (2026)
- [LLMs are General Asynchronous Agents](https://mlsanity.com/paper/2609.35427/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable capabilities in chain of thought (CoT) reasoning. However, the current LLM reasoning paradigm initiates thinking only after the entire input is available, which introduces unnecessary latency and weakens attention to earlier information in dynamic scenarios. Inspired by human cognition of thinking while reading, we first design a textitstreaming thinking paradigm for LLMs, where reasoning unfolds in the order of input and further adjusts its depth once reading is complete. We instantiate this paradigm with textitStreamingThinker, a framework that enables LLMs to think while reading through the integration of streaming CoT generation, streaming-constraint training, and streaming parallel inference. Specifically, StreamingThinker employs streaming reasoning units with quality control for CoT generation, enforces order-preserving reasoning through streaming attention masks and position encoding, and leverages parallel KV caches that decouple input encoding from reasoning generation, thereby ensuring alignment and enabling true concurrency. We evaluate StreamingThinker on the Qwen3 model family across math reasoning, logical reasoning, and context-based QA reasoning tasks. Experimental results show that the StreamingThinker preserves performance comparable to batch thinking, while yielding an 80% reduction in token waiting before the onset of reasoning and a more than 60% reduction in time-level latency for producing the final answer, demonstrating the effectiveness of the streaming paradigm for LLM reasoning. Code is publicly available at https://github.com/EIT-NLP/StreamingLLM/tree/main/StreamingThinker.