# Never Stop Thinking: Continuous-Time Language Agents

arXiv: https://arxiv.org/abs/2609.17416 · HTML: https://mlsanity.com/paper/2609.17416/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 33)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [AudioBench: A Universal Benchmark for Audio Large Language Models](https://mlsanity.com/paper/2406.16020/) (2024)
- [MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction](https://mlsanity.com/paper/2604.27393/) (2026)
- [Language Model Can Listen While Speaking](https://mlsanity.com/paper/2408.02622/) (2024)
- [Step-Audio-R1 Technical Report](https://mlsanity.com/paper/2511.15848/) (2025)
- [STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models](https://mlsanity.com/paper/2507.15375/) (2025)
- [Continuous Thought Machines](https://mlsanity.com/paper/2505.05522/) (2025)
- [Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving](https://mlsanity.com/paper/2603.18897/) (2026)
- [SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models](https://mlsanity.com/paper/2510.06917/) (2025)
- [Asynchronous LLM Function Calling](https://mlsanity.com/paper/2412.07017/) (2024)
- [StreamingThinker: Large Language Models Can Think While Reading](https://mlsanity.com/paper/2510.17238/) (2025)
- [Real-Time Reasoning Agents in Evolving Environments](https://mlsanity.com/paper/2511.04898/) (2025)
- [Chronological Thinking in Full-Duplex Spoken Dialogue Language Models](https://mlsanity.com/paper/2510.05150/) (2025)
- [SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models](https://mlsanity.com/paper/2506.05745/) (2025)
- [Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models](https://mlsanity.com/paper/2510.09592/) (2025)
- [Are Large Reasoning Models Interruptible?](https://mlsanity.com/paper/2510.11713/) (2025)
- [Asynchronous Reasoning: Training-Free Interactive Thinking LLMs](https://mlsanity.com/paper/2512.10931/) (2025)

## Built on by (most cited first, 1 of 1)

- [StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams](https://mlsanity.com/paper/2609.38612/) (2026)

## Abstract (arXiv)

Voice agents built on LLMs follow a rigid listen-think-speak loop that inserts seconds of dead air before every reply. We show that continuous-time cognition (thinking while listening and thinking while speaking) emerges from an unmodified text model under a lightweight interrupt-and-resume orchestrator, cutting live-pipeline latency by 19% overall and by half in the regime the mechanism targets. To measure whether continuous-time thinking improves what agents accomplish, we introduce ReactiveBench: 120 interactive scenarios scored against pre-registered binary requirements, plus a verifiable streaming track scored by exact correctness. ReactiveBench exposes a pitfall with broad consequences: LLM judges reward visible reasoning; a large judged "advantage" of continuous-time thinking reverses sign under an independent judge, and judge-trained models objectively complete fewer requirements when they think. A five-stage training study then locates the right signal at three levels. Its source: verifiable objectives turn thinking from harmful to helpful. Its structure: whatever a uniform reward omits, optimization trades away; brevity everywhere erodes multi-hop tool chaining. Its optimizer: preference optimization can only trade conflicting sub-goals against each other, while on-policy RL over a type-shaped reward improves every correctness axis at once, raising streaming completion from 48% to 73+/-5% across seeds and replicating at larger scale and on a second model. Orchestration makes continuous-time interaction possible; a verifiable signal, correctly sourced, shaped, and optimized, makes it good.