arXiv cs.CL· Abhijit Chakraborty, Ashish Raj Shekhar, Shiven Agarwal, Vivek Gupta·· 14 小时前AI 评分31
DeALOG：基于共享日志的去中心化多智能体推理框架
DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework
AI 导读
DeALOG 是一个面向多模态问答的去中心化多智能体框架，由 Table、Context、Visual、Summarizing 和 Verification 等专用智能体通过共享自然语言日志作为持久记忆进行通信，无需中心控制即可实现协作式错误检测与验证。
正文 · 原文
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.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.00996 [cs.CL] |
| (or arXiv:2602.00996v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2602.00996 arXiv-issued DOI via DataCite |
Submission history
From: Abhijit Chakraborty [view email]
[v1]
Sun, 1 Feb 2026 03:26:52 UTC (2,885 KB)
[v2]
Sun, 21 Jun 2026 07:42:56 UTC (9,947 KB)
[v3]
Sun, 25 Oct 2026 06:43:47 UTC (589 KB)
来源：arXiv cs.CL · arxiv.org