mlsanityData to 14 Oct 2026

NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning

arXiv 2601.03790 ↗First posted 7 Jan 2026cs.CL cs.AIcited by 3

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Neologism-aware machine translation aims to translate source sentences containing neologisms into target languages. This field remains underexplored compared with general machine translation (MT). In this paper, we propose an agentic framework, NeoAMT, for neologism-aware machine translation equipped with a Wiktionary-based search toolkit. Specifically, we first construct a dedicated dataset for neologism-aware machine translation and build a search toolkit grounded in Wiktionary. The dataset covers 16 languages and 75 translation directions in total, derived from approximately 10 million records of an English Wiktionary dump. The retrieval corpus of the search toolkit is also constructed from around 3 million cleaned records of the same dump. We then leverage the dataset and toolkit to train a translation agent via reinforcement learning (RL) and to evaluate the accuracy of neologism-aware machine translation. Furthermore, we propose an RL training framework featuring a novel reward design and an adaptive rollout generation strategy that exploits translation difficulty to further improve the translation quality of translation agents using our search toolkit.

Key facts. Cited by 3 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 30 of its 47 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

30 of 47 references.

References · 30

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2017Billion-scale similarity search with GPUscited by 2,497
  4. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  5. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  6. 2025s1: Simple test-time scalingcited by 1,341
  7. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  8. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 420
  9. 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translationcited by 394
  10. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
  11. 2024Tower: An Open Multilingual Large Language Model for Translation-Related Taskscited by 206
  12. 2019CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEBcited by 177
18 more
  1. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 156
  2. 2024Aya 23: Open Weight Releases to Further Multilingual Progresscited by 123
  3. 2023Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Taskcited by 88
  4. 2025WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialectscited by 79
  5. 2023Benchmarking Machine Translation with Cultural Awarenesscited by 53
  6. 2025MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learningcited by 48
  7. 2024X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scalecited by 36
  8. 2024DRT: Deep Reasoning Translation via Long Chain-of-Thoughtcited by 29
  9. 2020A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERTcited by 27
  10. 2024NEO-BENCH: Evaluating Robustness of Large Language Models with Neologismscited by 20
  11. 2024Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignmentcited by 13
  12. 2025SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translationcited by 13
  13. 2025ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learningcited by 11
  14. 2023WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Predictioncited by 10
  15. 2023Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embeddingcited by 9
  16. 2025Test-Time Scaling of Reasoning Models for Machine Translationcited by 5
  17. 2024BinaryAlign: Word Alignment as Binary Sequence Labelingcited by 3
  18. 2025TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignmentcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Benchmarking Machine Translation on Chinese Social Media Textscited by 2
  2. 2026GRC: Unifying Reasoning-Driven Generation, Retrieval and Compressioncited by 0
  3. 2026CNeo-Bench: Diagnosing Large Language Models on Chinese Neologismscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design
  2. 2024Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution
  3. 2026Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation
  4. 2026Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning
  5. 2025Preserving Cultural Identity with Context-Aware Translation Through Multi-Agent AI Systems
  6. 2026PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning
  7. 2026GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation
  8. 2026Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation