# agentic-ger: terminology recovery in long-form speech using global context

arXiv: https://arxiv.org/abs/2609.29428 · HTML: https://mlsanity.com/paper/2609.29428/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 15 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

- LLM agents and tool use

## Builds on (most cited first, 15 of 15)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning](https://mlsanity.com/paper/2505.17813/) (2025)
- [Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting](https://mlsanity.com/paper/2309.15649/) (2023)
- [Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition](https://mlsanity.com/paper/2306.16007/) (2023)
- [HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models](https://mlsanity.com/paper/2309.15701/) (2023)
- [Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!](https://mlsanity.com/paper/2504.09762/) (2025)
- [Fun-ASR Technical Report](https://mlsanity.com/paper/2509.12508/) (2025)
- [Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models](https://mlsanity.com/paper/2405.10025/) (2024)
- [Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation](https://mlsanity.com/paper/2410.13198/) (2024)
- [Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions](https://mlsanity.com/paper/2407.17874/) (2024)
- [LongSpeech: A Scalable Benchmark for Transcription, Translation and Understanding in Long Speech](https://mlsanity.com/paper/2601.13539/) (2026)
- [GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark](https://mlsanity.com/paper/2606.28884/) (2026)
- [Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations](https://mlsanity.com/paper/2606.13464/) (2026)

## Abstract (arXiv)

Recent advances in speech language models have improved automatic speech recognition (ASR) for long-form audio. However, accurately and consistently transcribing domain-specific terminology remains challenging. Motivated by the world knowledge and contextual capability of large language models (LLMs), we propose Agentic-GER, an LLM-based agent for terminology correction in long-form speech. The agent uses global context from the full transcript to identify suspicious terms and resolve ambiguous hypotheses. It selectively re-transcribes the source speech to check candidate corrections, and uses accepted edits to guide subsequent decisions. Experiments with four LLMs and two ASR systems on GigaSpeechBench show consistent terminology improvements in both Chinese and English, with and without thinking. On Chinese speech, Agentic-GER achieves up to a 36.8% relative reduction in biased character error rate (B-CER) over the Whisper baseline.