DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework
This addresses the problem of integrating diverse information sources for complex question answering, offering a modular and interpretable approach, though it appears incremental as an extension of agent-based methods.
The paper tackles multimodal question answering across text, tables, and images by introducing DeALOG, a decentralized multi-agent framework where specialized agents communicate via a shared natural-language log, achieving competitive performance on six benchmarks including FinQA and MultiModalQA.
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.