arXiv:2608. 03372v1 Announce Type: cross Abstract: AI systems rewrite information constantly: conversations become stored memories, documents become answers.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2607. 22962v1 Announce Type: new Abstract: LLM agents that operate over many turns accumulate facts in an external memory store and reuse them as premises for downstream reasoning.
arXiv:2609.22818v1 Announce Type: cross Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adv...
A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains.
Mnemon is a memory agent that stores conversations as raw, dated records and uses a fast System 1 decision model (Jev) to quickly judge the relevance of records, while a slow System 2 LLM plans searches and composes answers. The agent consolidates records into topic timelines and value histories in the background, enabling efficient retrieval without rewriting conversations into structured formats. Experiments show Mnemon achieving high scores on LoCoMo and LongMemEval‑S with low context length and cost, and Jev outperforming LLMs in evidence separation and speed.
arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.
arXiv:2606. 22030v2 Announce Type: replace Abstract: We investigate when belief-based memory actually improves large language model (LLM) agents.