mlsanityData to 13 Oct 2026

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

arXiv 1609.00777 ↗First posted 3 Sep 2016cs.CL cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

This paper proposes KB-InfoBot -- a multi-turn dialogue agent which helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to access real-world knowledge. Previous systems achieved this by issuing a symbolic query to the KB to retrieve entries based on their attributes. However, such symbolic operations break the differentiability of the system and prevent end-to-end training of neural dialogue agents. In this paper, we address this limitation by replacing symbolic queries with an induced "soft" posterior distribution over the KB that indicates which entities the user is interested in. Integrating the soft retrieval process with a reinforcement learner leads to higher task success rate and reward in both simulations and against real users. We also present a fully neural end-to-end agent, trained entirely from user feedback, and discuss its application towards personalized dialogue agents. The source code is available at https://github.com/MiuLab/KB-InfoBot.

Key facts. Cited by 36 papers in the map (data through 13 Oct 2026). First posted on arXiv 3 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 14; 2022: 8; 2023: 6; 2024: 3; 2025: 2; 2026: 2.

36 papers.

Sort:

By area:

  1. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  2. 2023The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Valuescited by 54
  3. 2021Transferable Dialogue Systems and User Simulatorscited by 35
  4. 2021Conversational Question Answering: A Surveycited by 31
  5. 2023LLMRec: Benchmarking Large Language Models on Recommendation Taskcited by 30
  6. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  7. 2023Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Gamescited by 24
  8. 2024Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generationcited by 22
  9. 2024ChatShop: Interactive Information Seeking with Language Agentscited by 22
  10. 2025Process-Supervised Reinforcement Learning for Code Generationcited by 22
  11. 2022Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learningcited by 21
  12. 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directionscited by 17
24 more
  1. 2022Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue Systemcited by 16
  2. 2018Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learningcited by 12
  3. 2021Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformerscited by 8
  4. 2021Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generationcited by 8
  5. 2022Conversational Agents: Theory and Applicationscited by 8
  6. 2023Conversational Question Answering with Reformulations over Knowledge Graphcited by 4
  7. 2021High-Quality Diversification for Task-Oriented Dialogue Systemscited by 3
  8. 2022Locally Aggregated Feature Attribution on Natural Language Model Understandingcited by 3
  9. 2022REKnow: Enhanced Knowledge for Joint Entity and Relation Extractioncited by 3
  10. 2021WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialoguecited by 2
  11. 2022NLU for Game-based Learning in Real: Initial Evaluationscited by 2
  12. 2022End-to-End Evaluation of a Spoken Dialogue System for Learning Basic Mathematicscited by 2
  13. 2023Successor Features for Efficient Multisubject Controlled Text Generationcited by 2
  14. 2021Converse, Focus and Guess -- Towards Multi-Document Driven Dialoguecited by 1
  15. 2021Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Fieldcited by 1
  16. 2021A Neural Conversation Generation Model via Equivalent Shared Memory Investigationcited by 0
  17. 2021Feudal Reinforcement Learning by Reading Manualscited by 0
  18. 2021Knowledge Graph-enhanced Sampling for Conversational Recommender Systemcited by 0
  19. 2021Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Userscited by 0
  20. 2022Recent Progress in Conversational AIcited by 0
  21. 2024Leveraging Knowledge Graph Embedding for Effective Conversational Recommendationcited by 0
  22. 2025Optimizing Conversational Product Recommendation via Reinforcement Learningcited by 0
  23. 2026MAP-Law: Coverage-Driven Retrieval Control for Multi-Turn Legal Consultationcited by 0
  24. 2026Q&A or Document-Based? The Effects of Interface Type on How Screen Reader Users Access Interconnected Documentscited by 0