Multi-agent debate with tit-for-tat arguments and a judge LLM improves reasoning by preventing LLMs from locking into incorrect initial solutions.
Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
HULAT2 submitted three runs to the Spanish MER-TRANS 2026 track; a LangGraph multi-agent workflow with internal quality signals achieved the best SARI score (44.05) among them, outperforming a linear regeneration baseline.
citing papers explorer
-
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Multi-agent debate with tit-for-tat arguments and a judge LLM improves reasoning by preventing LLMs from locking into incorrect initial solutions.
-
HULAT2 at MER-TRANS 2026: Governed Multi-Agent Simplification for Spanish Easy-to-Read Generation
HULAT2 submitted three runs to the Spanish MER-TRANS 2026 track; a LangGraph multi-agent workflow with internal quality signals achieved the best SARI score (44.05) among them, outperforming a linear regeneration baseline.