# Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection

arXiv: https://arxiv.org/abs/2605.30274 · HTML: https://mlsanity.com/paper/2605.30274/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 28 May 2026.

## Placed in

- 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, 23 of 23)

- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Large language models effectively leverage document-level context for literary translation, but critical errors persist](https://mlsanity.com/paper/2304.03245/) (2023)
- [WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects](https://mlsanity.com/paper/2502.12404/) (2025)
- [o1-Coder: an o1 Replication for Coding](https://mlsanity.com/paper/2412.00154/) (2024)
- [Adapting Large Language Models for Document-Level Machine Translation](https://mlsanity.com/paper/2401.06468/) (2024)
- [Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metric](https://mlsanity.com/paper/2209.13654/) (2022)
- [Exploiting Cross-Sentence Context for Neural Machine Translation](https://mlsanity.com/paper/1704.04347/) (2017)
- [G-Transformer for Document-level Machine Translation](https://mlsanity.com/paper/2105.14761/) (2021)
- [When and Why is Document-level Context Useful in Neural Machine Translation?](https://mlsanity.com/paper/1910.00294/) (2019)
- [DRT: Deep Reasoning Translation via Long Chain-of-Thought](https://mlsanity.com/paper/2412.17498/) (2024)
- [TasTe: Teaching Large Language Models to Translate through Self-Reflection](https://mlsanity.com/paper/2406.08434/) (2024)
- [DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory](https://mlsanity.com/paper/2410.08143/) (2024)
- [Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis](https://mlsanity.com/paper/2502.11544/) (2025)
- [Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs](https://mlsanity.com/paper/2311.03127/) (2023)
- [Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning](https://mlsanity.com/paper/2504.21561/) (2025)
- [Multilingual Contextualization of Large Language Models for Document-Level Machine Translation](https://mlsanity.com/paper/2504.12140/) (2025)
- [AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration](https://mlsanity.com/paper/2509.19236/) (2025)
- [Source-primed Multi-turn Conversation Helps Large Language Models Translate Documents](https://mlsanity.com/paper/2503.10494/) (2025)
- [Doc-Guided Sent2Sent++: A Sent2Sent++ Agent with Doc-Guided memory for Document-level Machine Translation](https://mlsanity.com/paper/2501.08523/) (2025)
- [Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement](https://mlsanity.com/paper/2504.05614/) (2025)
- [Improving LLM-based Document-level Machine Translation with Multi-Knowledge Fusion](https://mlsanity.com/paper/2503.12152/) (2025)
- [MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics](https://mlsanity.com/paper/2602.23258/) (2026)

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

- [AI translation of literary texts is "fine", but readers still prefer human translations](https://mlsanity.com/paper/2606.26040/) (2026)

## Abstract (arXiv)

Document-level translation remains one of the most challenging tasks for large language models, which are constrained by limited context windows that impede global cohesion, while simultaneously suffering from redundant contextual information that degrades translation quality. To address this, we propose a human-like long document translation agent called Loong, which leverages a 3E memory module (Essence-Exemplar-Entity) to store summaries, sentence pairs, and entity records as historical context. Instead of passively attending to all history, Loong performs deep reasoning to adaptively identify the optimal context for translation guidance. Loong optimizes its context policy through reinforcement learning, utilizing preference data derived from its own sampled observe-and-act reasoning trajectories. Empirical evaluations demonstrate that Loong achieves substantial translation quality improvements in English Leftrightarrow Chinese, German, and French directions, with average gains of up to 13.0 points across the three evaluation metrics. Furthermore, Loong exhibits strong generalization across domains and robustness against contextual noise, while maintaining remarkable stability in ultra-long document translation. Our code is released at https://github.com/YutongWang1216/LoongDocMT.