HULAT2 at MER-TRANS 2026: Governed Multi-Agent Simplification for Spanish Easy-to-Read Generation
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 gener
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%langgenius/dify →
- PossiblePossibly related (embedding) · 48%Supervertaler/Supervertaler-Workbench →
- PossiblePossibly related (embedding) · 48%sgl-project/sglang →
- PossiblePossibly related (embedding) · 47%Pipelex/pipelex →
- PossiblePossibly related (embedding) · 47%langchain-ai/open-swe →
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “HULAT2 at MER-TRANS 2026: Governed Multi-Agent Simplificatio” ≈ “AgentCore-8B””
- LinkedLinked via arxiv author · 85%Lourdes Moreno →
“HULAT2 at MER-TRANS 2026: Governed Multi-Agent Simplification for Spanish Easy-to-Read Generation”
- LinkedLinked via arxiv author · 85%Paloma Martínez →
“HULAT2 at MER-TRANS 2026: Governed Multi-Agent Simplification for Spanish Easy-to-Read Generation”