--- title: "AIDA Agents: A Multi-Agent Translation Platform — Rosa 2026" description: "Localization teams in industry must choose between NMT engines that need costly fine-tuning and heavy post-editing, and LLMs that translate well but do…" authors: ["Emanuele Di Rosa", "Piotr Peszynski"] year: 2026 venue: "Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 2)" source: "https://aclanthology.org/2026.eamt-2.4/" licence: "CC BY-ND 4.0 (EAMT)" licence_url: "https://creativecommons.org/licenses/by-nd/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/rosa-2026-aida-agents-multi-agent-translation/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/rosa-2026-aida-agents-multi-agent-translation/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/) / AIDA Agents: A Multi-Agent Translation Platform with Context-Aware Quality Control # AIDA Agents: A Multi-Agent Translation Platform with Context-Aware Quality Control **Authors:** Emanuele Di Rosa, Piotr Peszynski · **Year:** 2026 · **Venue:** Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 2) · **Licence:** [CC BY-ND 4.0 (EAMT)](https://creativecommons.org/licenses/by-nd/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.eamt-2.4/) · [PDF](https://aclanthology.org/2026.eamt-2.4.pdf) ## Summary Localization teams in industry must choose between NMT engines that need costly fine-tuning and heavy post-editing, and LLMs that translate well but do not fit existing CAT/TMS workflows. AIDA Agents, from DATAmundi, addresses this with a pipeline of specialised LLM agents. Up to three translator agents draft candidates. An Arbiter/Rater scores them on MQM-inspired criteria (accuracy, fluency, terminology, style) and picks the best. A Post-Editor Agent revises that choice, and a second rating pass produces the final output. Optional RAG adds translation memories, glossaries and style guides at every step, so the system adapts to a domain without fine-tuning. Files go in and out as XLIFF, with their structure preserved. On WMT24++ (11 English→X pairs, no TM or terminology), AIDA scores the highest BLEU on 10 of 11 languages. On a small industrial IT benchmark, linguists judged most AIDA MultiLLM output publishable without human editing. The work shows that agent orchestration can compete with commercial MT and partly replace post-editing. The evaluation is preliminary, however, and is described in the paper as such. ## Key points - **Three product tiers.** AIDA LLM uses 3 calls per segment. AIDA MultiLLM uses up to 6 calls, with parallel translators, a rater, a post-editor and a re-rater. AIDA NMT uses 3 calls: an NMT engine plus an LLM post-editor and an LLM rater. - **WMT24++ results.** The test set has 960 segments in 4 domains. AIDA has the top BLEU in 10/11 languages, with the largest margin on Japanese (+3.9). Swahili is the exception, where it trails GPT-4o by 1.3. - **Industrial benchmark setup.** It covers 96 segments per language in 6 languages (JA, ZH, FR, KO, DE, ES) of technical IT documentation, with full TM, terminology and style guides. Three linguists per language rated output blindly on a 5-point scale. - **Industrial benchmark results.** AIDA MultiLLM had the highest BLEU in all six languages. Between 69.4% and 98.0% of its segments were rated Good/Excellent. - **Comparison with human post-editing.** AIDA's Good/Excellent share beat the human-post-edited competitor only for German (98.0% vs. 91.9%). The conclusion claims several language pairs, but Table 2 supports only German. The proposed 50–70% cut in post-editing effort is an estimate, not a measured result. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) · [Machine translation](https://md.research.elamur.ai/free/en/shelves/machine-translation/) Topics: [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{rosa2026aida, title = {{AIDA Agents: A Multi-Agent Translation Platform with Context-Aware Quality Control}}, author = {Rosa, Emanuele Di and Peszynski, Piotr}, booktitle = {Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 2)}, year = {2026}, url = {https://aclanthology.org/2026.eamt-2.4/} } ``` - [← previous AI Safety Lost in Translation: Evaluating the Effectiveness of English-Italian Cross-Lingual LLM Safety Alignment](https://md.research.elamur.ai/free/en/papers/wu-2026-ai-safety-lost-translation-evaluating/) - [next → Aladdin-FTI @ AMIYA Three Wishes for Arabic NLP: Fidelity, Diglossia, and Multidialectal Generation](https://md.research.elamur.ai/free/en/papers/mutal-2026-aladdin-fti-amiya-three-wishes/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/) ## References 3 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Daniel Deutsch et al. 2025. WMT24++: Expanding the language coverage of WMT24 to 55 languages & dialects. In Findings of ACL 2025, pages 12257– 12284. [find](https://scholar.google.com/scholar?q=Daniel+Deutsch+et+al%2E+2025%2E+WMT24%2B%2B%3A+Expanding+the+language+coverage+of+WMT24+to+55+languages+%26+dialects%2E+In+Findings+of+ACL+2025%2C+pages+12257%E2%80%93+12284%2E) 2. Emanuele Di Rosa. 2026. Multi-agent orchestration for terminology-constrained machine translation in industrial localization. In Proc. of ACL 2026: Industry Track. To appear. [find](https://scholar.google.com/scholar?q=Emanuele+Di+Rosa%2E+2026%2E+Multi%2Dagent+orchestration+for+terminology%2Dconstrained+machine+translation+in+industrial+localization%2E+In+Proc%2E+of+ACL+2026%3A+Industry+Track%2E+To+appear%2E) 3. George Wang et al. 2025. MAATS: A multi-agent automated translation system based on MQM evaluation. arXiv:2505.14848. [find](https://scholar.google.com/scholar?q=George+Wang+et+al%2E+2025%2E+MAATS%3A+A+multi%2Dagent+automated+translation+system+based+on+MQM+evaluation%2E+arXiv%3A2505%2E14848%2E)