ARGORA: Orchestrated Argumentation for Causally Grounded LLM Reasoning and Decision Making

TL;DR

ARGORA is a framework that structures multi-expert LLM discussions into causal argumentation graphs, enabling systematic analysis, correction, and improved decision-making transparency.

Contribution

It introduces explicit argumentation graphs for multi-expert LLMs, allowing causal analysis and correction of reasoning, which enhances interpretability and decision accuracy.

Findings

Achieves competitive accuracy across benchmarks

Effectively resolves disputes towards correct answers

Provides causal diagnostics of decisive arguments

Abstract

Existing multi-expert LLM systems gather diverse perspectives but combine them through simple aggregation, obscuring which arguments drove the final decision. We introduce ARGORA, a framework that organizes multi-expert discussions into explicit argumentation graphs showing which arguments support or attack each other. By casting these graphs as causal models, ARGORA can systematically remove individual arguments and recompute outcomes, identifying which reasoning chains were necessary and whether decisions would change under targeted modifications. We further introduce a correction mechanism that aligns internal reasoning with external judgments when they disagree. Across diverse benchmarks and an open-ended use case, ARGORA achieves competitive accuracy and demonstrates corrective behavior: when experts initially disagree, the framework resolves disputes toward correct answers more often than it introduces new errors, while providing causal diagnostics of decisive arguments.