# HULAT2 at MER-TRANS 2026: Governed Multi-Agent Simplification for Spanish Easy-to-Read Generation

arXiv: https://arxiv.org/abs/2607.02381 · HTML: https://mlsanity.com/paper/2607.02381/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [Findings of the TSAR-2022 Shared Task on Multilingual Lexical Simplification](https://mlsanity.com/paper/2302.02888/) (2023)
- [Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension](https://mlsanity.com/paper/2312.10126/) (2023)
- [Exploring Large Language Models to generate Easy to Read content](https://mlsanity.com/paper/2407.20046/) (2024)
- [Evaluating Document Simplification: On the Importance of Separately Assessing Simplicity and Meaning Preservation](https://mlsanity.com/paper/2404.03278/) (2024)
- [A Multilingual Human Annotated Corpus of Original and Easy-to-Read Texts to Support Access to Democratic Participatory Processes](https://mlsanity.com/paper/2603.05345/) (2026)
- [A Human-in/on-the-Loop Framework for Accessible Text Generation](https://mlsanity.com/paper/2603.18879/) (2026)

## Abstract (arXiv)

This paper describes the participation of HULAT2-UC3M in the Spanish track of MER-TRANS 2026, a shared task on multilingual Easy-to-Read translation. Three fully automatic Spanish runs were submitted. RUN1 and RUN2 used a LangGraph-based multi-agent workflow combining Gemini 2.5 Flash and RigoChat-7B-v2, parallel generation strategies, internal quality signals, Event-Condition-Action routing, controlled editing and traceable decisions. RUN1 used the base workflow, while RUN2 activated an additional lexical-support layer based on a glossary and lexical resources. RUN3 was a RigoChat-based generate-evaluate-regenerate baseline with prompt engineering and LoRA-based adaptation. The official leaderboard reports BLEU-Orig, BLEU-Gold, SARI and BERTScore. During development, additional internal signals were also inspected, including semantic fidelity, readability, lexical simplicity, syntactic clarity and factual consistency. According to official SARI, RUN1 was the best HULAT2 run, with 44.0543 points, followed by RUN2 with 43.1049 and RUN3 with 38.5136. These results indicate that, in this task setting, signal-guided multi-agent routing outperformed the linear regeneration baseline. They also show that adding lexical support did not automatically improve reference-based scores. Further segment-level and document-level analysis are required to assess readability, factual consistency and user-oriented adequacy.