Memorix: Managing Memory Selections for AI Agents

arXiv:2611.00060v1 Announce Type: cross Abstract: AI agents now handle a growing share of tasks across sessions within a persistent project. Their behavior depends not only on the model, but heavily on the persistent state they read from the environment. Existing systems assemble this memory at use time, splicing selected files into the prompt as a one-off payload. As a result, per-task assembly is costly and can still miss critical material, failures cannot be traced or replayed, and agents can read documentation written for the wrong version. Our key insight is that what an agent should read is mostly determined by its project, so the selection can be computed once, ahead of time, and reused across tasks. We propose Memorix, an agent memory system that realizes this insight. Memorix achieves this via three key mechanisms: (1) an immutable and versioned Store pins every source by identity and reproduces historical layouts cheaply, (2) a View that splits selection (Derivations) from composition (Environment), making the result reproducible and shareable, and (3) Quests and Profiles keep a delivered view refreshable and available inside the project as sources evolve. We implement Memorix and evaluate it on SWE-ContextBench and LibEvolutionEval against mainstream agent memory systems. Precomputed Environments raise resolved rate by up to 1.5X and deliver the correct library version on every version-conditioned task, while cutting amortized cost by up to 100X and build time by up to 38X.

Abstract:AI agents now handle a growing share of tasks across sessions within a persistent project. Their behavior depends not only on the model, but heavily on the persistent state they read from the environment. Existing systems assemble this memory at use time, splicing selected files into the prompt as a one-off payload. As a result, per-task assembly is costly and can still miss critical material, failures cannot be traced or replayed, and agents can read documentation written for the wrong version. Our key insight is that what an agent should read is mostly determined by its project, so the selection can be computed once, ahead of time, and reused across tasks. We propose Memorix, an agent memory system that realizes this insight. Memorix achieves this via three key mechanisms: (1) an immutable and versioned Store pins every source by identity and reproduces historical layouts cheaply, (2) a View that splits selection (Derivations) from composition (Environment), making the result reproducible and shareable, and (3) Quests and Profiles keep a delivered view refreshable and available inside the project as sources evolve. We implement Memorix and evaluate it on SWE-ContextBench and LibEvolutionEval against mainstream agent memory systems. Precomputed Environments raise resolved rate by up to 1.5X and deliver the correct library version on every version-conditioned task, while cutting amortized cost by up to 100X and build time by up to 38X.

Operating Systems (cs.OS); Artificial Intelligence (cs.AI)

arXiv:2611.00060 [cs.OS]

(or arXiv:2611.00060v1 [cs.OS] for this version)

https://doi.org/10.48550/arXiv.2611.00060 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Memorix: Managing Memory Selections for AI Agents

Related coverage