mlsanityData to 14 Oct 2026

Personal AI Agent for Camera Roll VQA

arXiv 2606.05275 ↗First posted 3 Jun 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera roll and retrieve relevant photos to answer queries, ranging from simple factual questions (e.g., ``Name of the food I tried yesterday?'') to more open-ended ones (e.g., ``Recommend some dishes I have never eaten before''). Given the vast nature of the personal camera roll (i.e., multiple years, hundreds to thousands of photos), a successful AI assistant needs to understand a long-horizon, highly personalized visual content stream in order to navigate and locate the correct and/or relevant information. To support this, we collect and manually annotate questions that mimic real-world usage. The final dataset, camroll, contains 50 users, 31,476 images, and 2,500 QA pairs. We further design camroll-agent, a conversational AI agent equipped with hierarchical memory and a minimal set of tools for efficient navigation over large, personalized visual memory. Experimental results show that camroll-agent outperforms numerous baselines and methods for long-context understanding AI agents system. Together, the camroll dataset and camroll-agent highlight the gap in AI agents' long-context reasoning: personalized visual memory requires different approaches from standard long-context textual memory, especially when consistency, visual details, and user-specific context are present.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

24 of 47 references.

References · 24

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2015VQA: Visual Question Answeringcited by 2,506
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  7. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  8. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
  9. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  10. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  11. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 180
  12. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
12 more
  1. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 149
  2. 2025Context Length Alone Hurts LLM Performance Despite Perfect Retrievalcited by 127
  3. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Modelscited by 73
  4. 2024Yo'LLaVA: Your Personalized Language and Vision Assistantcited by 62
  5. 2023RealFill: Reference-Driven Generation for Authentic Image Completioncited by 59
  6. 2024Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmarkcited by 55
  7. 2025YoChameleon: Personalized Vision and Language Generationcited by 20
  8. 2026According to Me: Long-Term Personalized Referential Memory QAcited by 14
  9. 2026PersonaVLM: Long-Term Personalized Multimodal LLMscited by 11
  10. 2026DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Historiescited by 6
  11. 2017Recognizing and Curating Photo Albums via Event-Specific Image Importancecited by 2
  12. 2026PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrievalcited by 2

Built on by

Not cited yet.