PulseAugur
EN
LIVE 07:46:44

HULAT2-UC3M uses multi-agent Gemini and RigoChat for Spanish Easy-to-Read translation task

By PulseAugur Editorial · [1 sources] ·

The HULAT2-UC3M team participated in the MER-TRANS 2026 Spanish Easy-to-Read translation task with three distinct approaches. Their primary method, RUN1, utilized a LangGraph-based multi-agent workflow incorporating Gemini 2.5 Flash and RigoChat-7B-v2, achieving the highest SARI score of 44.0543. A second approach, RUN2, added a lexical-support layer to the multi-agent workflow but resulted in a slightly lower SARI score. A baseline approach, RUN3, employed a generate-evaluate-regenerate strategy with prompt engineering and LoRA adaptation, scoring 38.5136 on the SARI metric. AI

IMPACT Demonstrates advanced multi-agent workflows for specialized text generation tasks.

RANK_REASON The item is an academic paper detailing participation in a shared task and presenting model results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

HULAT2-UC3M uses multi-agent Gemini and RigoChat for Spanish Easy-to-Read translation task

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Lourdes Moreno, Paloma Mart\'inez, Marco Antonio Sanchez-Escudero, Miguel Dom\'inguez-G\'omez ·

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

    arXiv:2607.02381v1 Announce Type: new Abstract: 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-…

RELATED ENTITIES

RELATED TOPICS