# From Argument Components to Graphs: A Multi-Agent Debate with Confidence Gating for Argument Relations

arXiv: https://arxiv.org/abs/2606.16047 · HTML: https://mlsanity.com/paper/2606.16047/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 16 of 16)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Parsing Argumentation Structures in Persuasive Essays](https://mlsanity.com/paper/1604.07370/) (2016)
- [Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?](https://mlsanity.com/paper/2508.17536/) (2025)
- [Argumentation Mining in User-Generated Web Discourse](https://mlsanity.com/paper/1601.02403/) (2016)
- [Argument Mining with Structured SVMs and RNNs](https://mlsanity.com/paper/1704.06869/) (2017)
- [Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning](https://mlsanity.com/paper/2511.07784/) (2025)
- [ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration](https://mlsanity.com/paper/2411.00053/) (2024)
- [Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach](https://mlsanity.com/paper/2506.16335/) (2025)
- [Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System](https://mlsanity.com/paper/2507.02170/) (2025)
- [Retrieval- and Argumentation-Enhanced Multi-Agent LLMs for Judgmental Forecasting (Extended Version with Supplementary Material)](https://mlsanity.com/paper/2510.24303/) (2025)
- [AMELIA: A Family of Multi-task End-to-end Language Models for Argumentation](https://mlsanity.com/paper/2508.17926/) (2025)
- [Multi-Agent Dialectical Refinement for Enhanced Argument Classification](https://mlsanity.com/paper/2603.27451/) (2026)
- [End-to-End Argument Mining through Autoregressive Argumentative Structure Prediction](https://mlsanity.com/paper/2510.16363/) (2025)
- [A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2](https://mlsanity.com/paper/2603.19253/) (2026)

## Built on by (most cited first, 1 of 1)

- [From Contexts to Values: Context-Dependent Defeat in Abstract Argumentation](https://mlsanity.com/paper/2608.15536/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly assessed and utilized in the field of Argument Mining (AM), thanks to their strong general reasoning capabilities. However, standard training-free models often miss sophisticated details, specifically in contexts where two parts of the text have to be analyzed together. Furthermore, self-correction mechanisms tend to reinforce initial hallucinations in reasoning. Overcoming these limitations typically requires expensive, domain-specific supervised fine-tuning. Recent work has shown that a multi-agent paradigm can address such weaknesses for the component classification task through dialectical refinement with a Proponent-Opponent-Judge architecture, setting a promising direction for training-free approaches in the field. In this paper, we extend and evaluate this framework on the Argument Relation Identification and Classification (ARIC) task, reformulating it as a debate over component pairs. Besides that, we introduce a confidence gating mechanism that enables debating only on the uncertain cases and accepting the initial prediction when confidence is high. On the UKP Argument Annotated Essays v2 corpus, we demonstrate that the selective debate achieves the highest Macro F1 among all training-free methods, while debate over all samples degrades performance below that of one of the baselines. All generative approaches also outperform fine-tuned RoBERTa models on Macro F1, suggesting that the under-representation of the Attack class was more damaging to supervised fine-tuning than to inference-only models. Additionally, our framework produces human-readable debate transcripts, offering interpretability absent from both single-agent and supervised classifiers.