mlsanityData to 7 Oct 2026

DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework

arXiv 2602.00996 ↗First posted 1 Feb 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 72 references that are in the map. First posted on arXiv 1 Feb 2026.

Builds on

40 of 72 references.

References · 40

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  5. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  6. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  7. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
  8. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 552
  9. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  10. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  11. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  12. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 420
28 more
  1. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  2. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 327
  3. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
  4. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  5. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  6. 2022Binding Language Models in Symbolic Languagescited by 224
  7. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  8. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 177
  9. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  10. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  11. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 174
  12. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  13. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72
  14. 2025MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understandingcited by 66
  15. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Modelcited by 56
  16. 2024Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversationscited by 43
  17. 2023Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Tablecited by 40
  18. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decompositioncited by 39
  19. 2025Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoningcited by 32
  20. 2022TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Datacited by 19
  21. 2024TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Datacited by 19
  22. 2024Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoningcited by 16
  23. 2024MMCTAgent: Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoningcited by 13
  24. 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answeringcited by 13
  25. 2025ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QAcited by 12
  26. 2024CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chartcited by 4
  27. 2025Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspectivecited by 4
  28. 2025Adaptive Multi-Agent Reasoning via Automated Workflow Generationcited by 1

Built on by

Not cited yet.