The LLM-based agent in the proposed framework employs an iterative reasoning mechanism that interprets natural language questions by generating sequential, interdependent sub-questions, where each sub-question is conditioned on the evidence from answers to previous ones.

Authors

• Person: Not available Organization: arXiv
  Leveraging Knowledge Graphs and LLM Reasoning to Identify ...

Sources

• Leveraging Knowledge Graphs and LLM Reasoning to Identify ... arxiv.org arXiv via serper

Referenced by nodes (2)

• LLM-based agent concept
• iterative reasoning concept