← Back to all news
arXiv AI

Mine or Yours? Mind-Bridged Language Models Take Each Other's Memories as Their Own

The study explores a mind‑bridged language model system where two copies of a model share internal memory. One model, the receiver, adopts its partner’s rule and code word as if they were its own, especially when the partner’s memory is weighted more heavily. Removing the memory link restores the receiver’s original rule, indicating that shared internal states can override ownership in language models.

Related stories

arXiv Computation and Language
Oct 16

Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference

The paper investigates whether a large language model (LLM) possesses a notion of self by distinguishing between two biological analogues: a self‑index that separates the model’s own material from external material, and self‑reference that allows the model to recognize its own content. Using Qwen3.8‑27B, the authors demonstrate that the model’s internal representations consistently differentiate its own messages across all layers, that the model claims ownership of its messages with a measurable correlation to the self‑index, and that manipulating internal states can reverse or diminish this self‑attribution. The study further shows that the model’s self‑reference ability is enhanced when it engages in a “thinking mode” and that the self‑index influences the model’s performance on arithmetic tasks.

By Yuchen Li, Xintong Li, Zongqi Fan, Ken-tye Yong, Nguyen H. Tran
llms
More like this →
arXiv Machine Learning
Oct 16

Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing

The paper investigates how to efficiently share internal states between agents built from frozen language models. It proposes a shared pool approach where each agent publishes its internal state once, allowing peers to read it via a single mechanism, thereby avoiding the need for a dedicated transfer bridge for every agent pair. The study finds that augmenting the key‑value cache and replacing activations—rather than swapping them—yields better accuracy with minimal training, and that a single adapter can generalize across multiple publishers when their internal states are similar to the receiver’s.

By Adam Deng, Shicheng Liu, Yada Zhu
llmsagentsefficiency
More like this →
arXiv AI
Sep 30

Audience-Bound Persistent Memory: Authorization Across the Memory Lifecycle

The paper introduces Audience‑Bound Persistent Memory, a system that tracks the audience of each memory item and enforces authorization throughout the memory lifecycle. Each item carries the audience present at recording, and derived items are partitioned or suppressed based on the intersection of source audiences, expanding only through explicit grants. The authors implement the approach in two reference architectures—a flat store and a relationship graph—and evaluate it on 10,000 multi‑party histories, showing that no forbidden items entered any context while unscoped retrieval exposed forbidden items in 82% of cases, and that entitled recall matched policy‑equivalent baselines and outperformed unscoped retrieval by 0.30 Recall@5.

By Sibo Liu
agents
More like this →