Memory and new controls for ChatGPT

Dreaming: Better memory for a more helpful ChatGPT

ChatGPT introduces a new memory system to better remember preferences, keeping context fresh and relevant across conversations.

Personalizing ChatGPT

Learn how to personalize ChatGPT using custom instructions and memory to get more relevant, consistent, and tailored responses.

New ways to manage your data in ChatGPT

ChatGPT users can now turn off chat history, allowing you to choose which conversations can be used to train our models.

Custom instructions for ChatGPT

We’re rolling out custom instructions to give you more control over how ChatGPT responds. Set your preferences, and ChatGPT will keep them in mind for all future conversations.

ChatGPT can now see, hear, and speak

When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents

arXiv:2606. 06055v1 Announce Type: new Abstract: Long-term memory enables language model agents to support personalized interactions, but it remains unclear when available memories warrant integration into responses.

AMU:Admission and Memory Update for Personalized Conversations---Structured Memory with SLM Guided Control

arXiv:2609.36976v1 Announce Type: new Abstract: Large language models (LLMs) have become the foundation of personalized assistants, but maintaining persistent user memory across long-term interaction...

Mitigating Over-Personalization in LLMs via Structured Memory

arXiv:2608. 08300v1 Announce Type: new Abstract: Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions.

PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?

arXiv:2602. 01146v2 Announce Type: replace Abstract: Conversational assistants are increasingly integrating long-term memory with large language models (LLMs).

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents

The paper introduces Temporal Semantic Memory (TSM), a framework that improves how large language model agents manage memory by addressing two key shortcomings: temporal inaccuracy and temporal fragmentation. TSM constructs a semantic timeline instead of a dialogue timeline, consolidating temporally continuous and semantically related information into durative memory. During retrieval, it aligns the query’s temporal intent with the semantic timeline, enabling the use of temporally appropriate durative memories and yielding up to a 12.2% accuracy boost over existing methods.

Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization

Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We formalize this setting as streaming dialogue summarization, where a system must summarize a current window using selective memory from an unbounded history under a fixed budget.

RUMBA: Russian User Memory Benchmark

arXiv:2607. 21447v1 Announce Type: cross Abstract: The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate retrieval metrics, failing to capture interactions between long-range context, temporal information, and reasoning.