DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework

TL;DR

DeALOG is a decentralized multi-agent framework for multimodal question answering that uses a shared natural-language log to coordinate specialized agents, enhancing robustness and interpretability.

Contribution

It introduces a novel decentralized multi-agent architecture with a shared log for multimodal QA, improving robustness and scalability over existing methods.

Findings

Achieves competitive performance on multiple QA benchmarks.

Shared log and agent verification significantly improve accuracy.

Modular design enables scalable and interpretable reasoning.

Abstract

Complex question answering across text, tables and images requires integrating diverse information sources. A framework supporting specialized processing with coordination and interpretability is needed. We introduce DeALOG, a decentralized multi-agent framework for multimodal question answering. It uses specialized agents: Table, Context, Visual, Summarizing and Verification, that communicate through a shared natural-language log as persistent memory. This log-based approach enables collaborative error detection and verification without central control, improving robustness. Evaluations on FinQA, TAT-QA, CRT-QA, WikiTableQuestions, FeTaQA, and MultiModalQA show competitive performance. Analysis confirms the importance of the shared log, agent specialization, and verification for accuracy. DeALOG, provides a scalable approach through modular components using natural-language communication.