arXiv (OAI Expanded)
open access
What It Costs to Compose, Rebuild, and Correct Precomputed Memory
Language models can answer from precomputed memory, a model's saved reading of a body of material, reused across requests instead of read again at each. This paper maps where that practice preserves correctness and the conditions under which it fails. Across experiments on Llama-3.1-8B-Instruct usin
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- What It Costs to Compose, Rebuild, and Correct Precomputed Memory#818703
- ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation#1131923
- Libra: Efficient Resource Management for Agentic RL Post-Training#1011120
- Skill Reuse as Compression in Agentic RL#819382
- Skill Reuse as Compression in Agentic RL#809389
Record · ID 808711
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive