# AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning

arXiv: https://arxiv.org/abs/2510.16156 · HTML: https://mlsanity.com/paper/2510.16156/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 8 of its 9 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- 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, 8 of 8)

- [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)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval](https://mlsanity.com/paper/2412.12009/) (2024)
- [Asynchronous Tool Usage for Real-Time Agents](https://mlsanity.com/paper/2410.21620/) (2024)
- [Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap](https://mlsanity.com/paper/2509.26542/) (2025)
- [Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting](https://mlsanity.com/paper/2501.04341/) (2025)
- [Dialogue-based Explanations for Logical Reasoning using Structured Argumentation](https://mlsanity.com/paper/2502.11291/) (2025)

## Built on by (most cited first, 2 of 2)

- [Bridging the Perception Gap: A Lightweight Coarse-to-Fine Architecture for Edge Audio Systems](https://mlsanity.com/paper/2601.15676/) (2026)
- [LLMs are General Asynchronous Agents](https://mlsanity.com/paper/2609.35427/) (2026)

## Abstract (arXiv)

Effective human-AI collaboration on complex reasoning tasks requires that users understand and interact with the model's process, not just receive an output. However, the monolithic text from methods like Chain-of-Thought (CoT) prevents this, as current interfaces lack real-time verbalization and robust user barge-in. We present AsyncVoice Agent, a system whose asynchronous architecture decouples a streaming LLM backend from a conversational voice frontend. This design allows narration and inference to run in parallel, empowering users to interrupt, query, and steer the model's reasoning process at any time. Objective benchmarks show this approach reduces interaction latency by more than 600x compared to monolithic baselines while ensuring high fidelity and competitive task accuracy. By enabling a two-way dialogue with a model's thought process, AsyncVoice Agent offers a new paradigm for building more effective, steerable, and trustworthy human-AI systems for high-stakes tasks.