mlsanityData to 14 Oct 2026

Knowledge acquisition for dialogue agents using reinforcement learning on graph representations

arXiv 2406.19500 ↗First posted 27 Jun 2024cs.AI cs.CLcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent models its knowledge as an RDF knowledge graph, integrating new beliefs acquired through conversation. Responses in dialogue are generated by identifying graph patterns around these new integrated beliefs. We show that policies can be learned using reinforcement learning to select effective graph patterns during an interaction, without relying on explicit user feedback. Within this context, our study is a proof of concept for leveraging users as effective sources of information.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 4 of its 22 references that are in the map. First posted on arXiv 27 Jun 2024.

Builds on

4 of 22 references.

References · 4

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  3. 2019Relational Graph Attention Networkscited by 82
  4. 2021EMISSOR: A platform for capturing multimodal interactions as Episodic Memories and Interpretations with Situated Scenario-based Ontological Referencescited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations
  2. 2025SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
  3. 2025Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
  4. 2019Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts
  5. 2024Towards a Zero-Data, Controllable, Adaptive Dialog System
  6. 2022A Mixture-of-Expert Approach to RL-based Dialogue Management
  7. 2024AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data
  8. 2024Input Conditioned Graph Generation for Language Agents