# Knowing the User Is Not Knowing What We Established: Grounding Awareness in Personal Agents

arXiv: https://arxiv.org/abs/2610.18684 · HTML: https://mlsanity.com/paper/2610.18684/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [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)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions](https://mlsanity.com/paper/2310.15421/) (2023)
- [Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs](https://mlsanity.com/paper/2502.09597/) (2025)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [Grounding Gaps in Language Model Generations](https://mlsanity.com/paper/2311.09144/) (2023)
- [Grounding Conversations with Improvised Dialogues](https://mlsanity.com/paper/2004.09544/) (2020)
- [CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions](https://mlsanity.com/paper/2508.01674/) (2025)
- [GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations](https://mlsanity.com/paper/2605.14498/) (2026)
- [Conversational Grounding: Annotation and Analysis of Grounding Acts and Grounding Units](https://mlsanity.com/paper/2403.16609/) (2024)
- [From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions](https://mlsanity.com/paper/2502.13791/) (2025)
- [SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie Script](https://mlsanity.com/paper/2410.20682/) (2024)
- [MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations](https://mlsanity.com/paper/2607.12893/) (2026)
- [Towards Harnessing Large Language Models for Comprehension of Conversational Grounding](https://mlsanity.com/paper/2406.01749/) (2024)
- [OpenJarvis: Personal AI, On Personal Devices](https://mlsanity.com/paper/2605.17172/) (2026)
- [Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs](https://mlsanity.com/paper/2601.09365/) (2026)

## Abstract (arXiv)

Personal-agent memory has largely focused on learning what users know, prefer, and want. However, knowing the user does not necessarily mean knowing what the user and the agent have established together. An assistant's proposal should not become an authorized instruction merely because it is remembered. We introduce Grounding Awareness, the ability to distinguish accepted, unacknowledged, revised, and scoped arrangements when selecting actions. We develop a controlled benchmark to test whether agents can tell the difference between proposals users have accepted and those they have not, and whether they apply accepted arrangements only where appropriate. Across multiple agents and memory systems, we find that strong memory performance does not ensure Grounding Awareness. More surprisingly, providing more complete user information can increase execution of unacknowledged proposals, while persistent memory can cause agents to treat these proposals as if they were user instructions. We trace these failures through memory writing, retrieval, and action selection. Finally, we introduce Grounding Layer, a lightweight, training-free extension that explicitly tracks grounding status and checks consequential actions, substantially improving agent behavior without modifying models or memory systems.