# RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

arXiv: https://arxiv.org/abs/2610.01780 · HTML: https://mlsanity.com/paper/2610.01780/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 64 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 30 of 33)

- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory](https://mlsanity.com/paper/2512.06688/) (2025)
- [Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset](https://mlsanity.com/paper/2507.09650/) (2025)
- [AI PERSONA: Towards Life-long Personalization of LLMs](https://mlsanity.com/paper/2412.13103/) (2024)
- [CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions](https://mlsanity.com/paper/2508.01674/) (2025)
- [HorizonBench: Long-Horizon Personalization with Evolving Preferences](https://mlsanity.com/paper/2604.17283/) (2026)
- [The Need for a Socially-Grounded Persona Framework for User Simulation](https://mlsanity.com/paper/2601.07110/) (2026)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue](https://mlsanity.com/paper/2601.19922/) (2026)
- [LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings](https://mlsanity.com/paper/2510.08338/) (2025)
- [BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs](https://mlsanity.com/paper/2603.16557/) (2026)
- [AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment](https://mlsanity.com/paper/2603.26680/) (2026)
- [Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces](https://mlsanity.com/paper/2604.08362/) (2026)
- [Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents](https://mlsanity.com/paper/2608.14606/) (2026)
- [When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses](https://mlsanity.com/paper/2607.26348/) (2026)
- [CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship](https://mlsanity.com/paper/2608.02046/) (2026)
- [The Rise of AI Companions: Interaction with AI Companions and Psychological Well-being](https://mlsanity.com/paper/2506.12605/) (2025)
- [Affective Flow Language Model for Emotional Support Conversation](https://mlsanity.com/paper/2602.08826/) (2026)
- [AffectVerse: Emotional World Models for Multimodal Affective Computing](https://mlsanity.com/paper/2605.19950/) (2026)
- [From Stateless to Situated: Building a Psychological World for LLM-Based Agents](https://mlsanity.com/paper/2603.25031/) (2026)
- [DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories](https://mlsanity.com/paper/2604.20443/) (2026)
- [OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling](https://mlsanity.com/paper/2605.26322/) (2026)
- [Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers](https://mlsanity.com/paper/2606.02776/) (2026)
- [Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games](https://mlsanity.com/paper/2606.17657/) (2026)
- [Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companions](https://mlsanity.com/paper/2607.28818/) (2026)

## Abstract (arXiv)

An AI companion that talks with someone for months should come to understand them. It should know who they are, remember what they said, and recognize when something from the past matters now. Testing this needs real conversations, but real conversations are private, so existing benchmarks use invented people and invented questions. We release RealCompanion, ten real relationships between people and an AI companion, with 27,218 messages over up to 120 days. For each person, we release the full conversation, a profile, a persona, chat test items, and question test items. Every label points to the messages that support it, and every chat label comes with the reasoning that produced it. The real data shows three things. First, people rarely refer back. Only 3.4% of their messages depend on something said earlier, and when one does, the earlier message is usually far away (a median of 2,157 messages back). Averages hide this. Looking at the most recent messages finds the needed one 95.9% of the time overall, but only 2.2% of the time when it is far back. Second, AI systems cannot tell when the past matters. The detectors we tested barely beat chance on real messages, and when the same earlier messages are labeled "memories" instead of "earlier messages", models bring up the past 10 to 14 percentage points more often, even when nothing from the past is needed. Third, AI systems read more into a person than the person revealed. Three agent systems rebuild each persona equally well (F1 0.71). They see the person, and then imagine more. Understanding a person depends on knowing when their past matters and where what they shared ends, and only real conversations can test it.