AgenticAI-DialogGen: Topic-Guided Conversation Generation for Fine-Tuning and Evaluating Short- and Long-Term Memories of LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Perera, Manoj Madushanka, Mahmood, Adnan, Wijethilake, Kasun Eranda, Sheng, Quan Z.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917406106976256
author Perera, Manoj Madushanka
Mahmood, Adnan
Wijethilake, Kasun Eranda
Sheng, Quan Z.
author_facet Perera, Manoj Madushanka
Mahmood, Adnan
Wijethilake, Kasun Eranda
Sheng, Quan Z.
contents Recent advancements in Large Language Models (LLMs) have improved their ability to process extended conversational contexts, yet fine-tuning and evaluating short- and long-term memories remain difficult due to the absence of datasets that encode both short- and long-term conversational history. Existing conversational datasets lack memory grounding, overlook topic continuity, or rely on costly human annotation. To address these gaps, we introduce AgenticAI-DialogGen, a modular agent-based framework that generates persona-grounded and topic-guided conversations without human supervision. The framework uses LLM agents to extract knowledge graphs, identify topics, build speaker personas, and simulate topic-guided conversations from unstructured conversations. A QA module generates memory-grounded Question Answer (QA) pairs drawn from short- and long-term conversational histories. We also generated a new dataset entitled, TopicGuidedChat (TGC), where long-term memory is encoded as speaker-specific knowledge graphs and short-term memory as newly generated topic-guided conversations. Evaluations depict that AgenticAI-DialogGen yields higher conversational quality and LLMs fine-tuned on TGC dataset achieve improved performance on memory-grounded QA tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12179
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AgenticAI-DialogGen: Topic-Guided Conversation Generation for Fine-Tuning and Evaluating Short- and Long-Term Memories of LLMs
Perera, Manoj Madushanka
Mahmood, Adnan
Wijethilake, Kasun Eranda
Sheng, Quan Z.
Computation and Language
Information Retrieval
68T50, 68T30
I.2.7; H.3.3; I.2.4
Recent advancements in Large Language Models (LLMs) have improved their ability to process extended conversational contexts, yet fine-tuning and evaluating short- and long-term memories remain difficult due to the absence of datasets that encode both short- and long-term conversational history. Existing conversational datasets lack memory grounding, overlook topic continuity, or rely on costly human annotation. To address these gaps, we introduce AgenticAI-DialogGen, a modular agent-based framework that generates persona-grounded and topic-guided conversations without human supervision. The framework uses LLM agents to extract knowledge graphs, identify topics, build speaker personas, and simulate topic-guided conversations from unstructured conversations. A QA module generates memory-grounded Question Answer (QA) pairs drawn from short- and long-term conversational histories. We also generated a new dataset entitled, TopicGuidedChat (TGC), where long-term memory is encoded as speaker-specific knowledge graphs and short-term memory as newly generated topic-guided conversations. Evaluations depict that AgenticAI-DialogGen yields higher conversational quality and LLMs fine-tuned on TGC dataset achieve improved performance on memory-grounded QA tasks.
title AgenticAI-DialogGen: Topic-Guided Conversation Generation for Fine-Tuning and Evaluating Short- and Long-Term Memories of LLMs
topic Computation and Language
Information Retrieval
68T50, 68T30
I.2.7; H.3.3; I.2.4
url https://arxiv.org/abs/2604.12179