# Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning

arXiv: https://arxiv.org/abs/2503.07018 · HTML: https://mlsanity.com/paper/2503.07018/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [Retrieval meets Long Context Large Language Models](https://mlsanity.com/paper/2310.03025/) (2023)
- [Jasper and Stella: distillation of SOTA embedding models](https://mlsanity.com/paper/2412.19048/) (2024)
- [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023)
- [Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations](https://mlsanity.com/paper/2310.13420/) (2023)
- [PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering](https://mlsanity.com/paper/2402.16288/) (2024)
- [DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents](https://mlsanity.com/paper/2406.13144/) (2024)

## Built on by (most cited first, 21 of 21)

- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026)
- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [HorizonBench: Long-Horizon Personalization with Evolving Preferences](https://mlsanity.com/paper/2604.17283/) (2026)
- [Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction](https://mlsanity.com/paper/2511.13410/) (2025)
- [How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants](https://mlsanity.com/paper/2601.16621/) (2026)
- [LLMs Corrupt Your Documents When You Delegate](https://mlsanity.com/paper/2604.15597/) (2026)
- [SteerX: Disentangled Steering for LLM Personalization](https://mlsanity.com/paper/2510.22256/) (2025)
- [LMEB: Long-horizon Memory Embedding Benchmark](https://mlsanity.com/paper/2603.12572/) (2026)
- [PM-Bench: Evaluating Prospective Memory in LLM Agents](https://mlsanity.com/paper/2607.12385/) (2026)
- [PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents](https://mlsanity.com/paper/2608.01708/) (2026)
- [DMT-CBT: Longitudinal Therapeutic State Modeling for CBT Counseling](https://mlsanity.com/paper/2606.03132/) (2026)
- [Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs](https://mlsanity.com/paper/2606.23283/) (2026)
- [PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue](https://mlsanity.com/paper/2608.06975/) (2026)
- [Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions](https://mlsanity.com/paper/2606.07893/) (2026)
- [Know It, Act on It: Investigating Memory Utilization in LLM Personalization](https://mlsanity.com/paper/2607.29433/) (2026)
- [hoBIT: A Profile-Aware Retrieval-Augmented Chatbot for University Academic Advising](https://mlsanity.com/paper/2608.26604/) (2026)
- [VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences](https://mlsanity.com/paper/2609.00921/) (2026)
- [PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations](https://mlsanity.com/paper/2609.09664/) (2026)
- [To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives](https://mlsanity.com/paper/2609.19167/) (2026)
- [Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives](https://mlsanity.com/paper/2610.01118/) (2026)

## Abstract (arXiv)

There has been a surge in the use of large language models (LLM) conversational agents to generate responses based on long-term history from multiple sessions. However, existing long-term open-domain dialogue datasets lack complex, real-world personalization and fail to capture implicit reasoning-where relevant information is embedded in subtle, syntactic, or semantically distant connections rather than explicit statements. In such cases, traditional retrieval methods fail to capture relevant context, and long-context modeling also becomes inefficient due to numerous complicated persona-related details. To address this gap, we introduce ImplexConv, a large-scale long-term dataset with 2,500 examples, each containing approximately 100 conversation sessions, designed to study implicit reasoning in personalized dialogues. Additionally, we propose TaciTree, a novel hierarchical tree framework that structures conversation history into multiple levels of summarization. Instead of brute-force searching all data, TaciTree enables an efficient, level-based retrieval process where models refine their search by progressively selecting relevant details. Our experiments demonstrate that TaciTree significantly improves the ability of LLMs to reason over long-term conversations with implicit contextual dependencies.