# DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework

Source: [DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e2314>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-24T05:00:22.884Z

Authors: Abhijit Chakraborty, Ashish Raj Shekhar, Shiven Agarwal, Vivek Gupta

Published: 2026-02-01T03:26:52.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.00996>)

[PDF](<https://arxiv.org/pdf/2602.00996.pdf>)