arXiv:2608. 11218v1 Announce Type: new Abstract: Independent agents that reason in latent space can share computed state as key-value cache fragments rather than text.
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:2609.24635v1 Announce Type: new Abstract: When a language model reads an operation such as "Swap the contents of Box F and Box B", its forward pass writes keys and values for those tokens into...
arXiv:2609.23371v1 Announce Type: cross Abstract: Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persisten...
Search agents now answer questions that take dozens of searches to settle, yet how such an agent reads a page has drawn far less attention than how it finds one. Nearly all of them use one of two document interfaces, and both tie a page to the moment it is opened.
arXiv:2609.22486v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on external sources when answering questions that require proprietary information or up-to-date live w...
arXiv:2609.14773v1 Announce Type: new Abstract: As LLM conversations grow to hundreds of turns, full-context injection incurs $O(N^2)$ cumulative token costs, while lossy summarization or hard trunca...
arXiv:2609.39661v1 Announce Type: new Abstract: Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value c...