mlsanityData to 7 Oct 2026

Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering

arXiv 2402.14320 ↗First posted 22 Feb 2024cs.CL cs.AIcited by 18

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Recent progress with LLM-based agents has shown promising results across various tasks. However, their use in answering questions from knowledge bases remains largely unexplored. Implementing a KBQA system using traditional methods is challenging due to the shortage of task-specific training data and the complexity of creating task-focused model structures. In this paper, we present Triad, a unified framework that utilizes an LLM-based agent with three roles for KBQA tasks. The agent is assigned three roles to tackle different KBQA subtasks: agent as a generalist for mastering various subtasks, as a decision maker for the selection of candidates, and as an advisor for answering questions with knowledge. Our KBQA framework is executed in four phases, involving the collaboration of the agent's multiple roles. We evaluated the performance of our framework using three benchmark datasets, and the results show that our framework outperforms state-of-the-art systems on the LC-QuAD and YAGO-QA benchmarks, yielding F1 scores of 11.8% and 20.7%, respectively.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 17 of its 33 references that are in the map. First posted on arXiv 22 Feb 2024.

Builds on

17 of 33 references.

References · 17

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  5. 2022A Survey on In-context Learningcited by 717
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  8. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  9. 2023Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answeringcited by 119
  10. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  11. 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agentscited by 83
  12. 2023Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Familycited by 71
5 more
  1. 2023ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions Towards Knowledge Graph Chatbotscited by 47
  2. 2023An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answeringcited by 19
  3. 2023A Universal Question-Answering Platform for Knowledge Graphscited by 17
  4. 2023Large Language Model for Science: A Study on P vs. NPcited by 12
  5. 2023Make a Choice! Knowledge Base Question Answering with In-Context Learningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 11; 2026: 4.

18 papers.

Sort:

By area:

  1. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 69
  2. 2025MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learningcited by 26
  3. 2024Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMscited by 22
  4. 2025SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflowscited by 12
  5. 2025PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimationcited by 8
  6. 2025iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answeringcited by 8
  7. 2025CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Taskscited by 8
  8. 2025SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injectioncited by 5
  9. 2025CLEAR-KGQA: Clarification-Enhanced Ambiguity Resolution for Knowledge Graph Question Answeringcited by 3
  10. 2026Yes FLoReNce, I Will Do Better Next Time! Agentic Feedback Reasoning for Humorous Meme Detectioncited by 3
  11. 2024ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responsescited by 2
  12. 2025HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communicationcited by 2
6 more
  1. 2025Automatic Transmission for LLM Tiers: Optimizing Cost and Accuracy in Large Language Modelscited by 1
  2. 2026AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answeringcited by 1
  3. 2025Re-Initialization Token Learning for Tool-Augmented Large Language Modelscited by 0
  4. 2025MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge Graphscited by 0
  5. 2026SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoningcited by 0
  6. 2026KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Joint Knowledge Base Completion and Question Answering by Combining Large Language Models and Small Language Models
  2. 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
  3. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering
  4. 2025A Survey of Large Language Model Agents for Question Answering
  5. 2024Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering
  6. 2026DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering
  7. 2025KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
  8. 2025Exemplar-Guided Planing: Enhanced LLM Agent for KGQA