[2605.30771] Eywa: Provenance-Grounded Long-Term Memory for AI Agents
= 0.5. Full per-question artifacts, including questions, gold answers, model answers, retrieved context, and labels, are published at https://eywa.to/research."/>
= 0.5. Full per-question artifacts, including questions, gold answers, model answers, retrieved context, and labels, are published at https://eywa.to/research." />
-->
Computer Science > Computation and Language
arXiv:2605.30771 (cs)
[Submitted on 29 May 2026]
Title:Eywa: Provenance-Grounded Long-Term Memory for AI Agents
Authors:Resham Joshi<br>View a PDF of the paper titled Eywa: Provenance-Grounded Long-Term Memory for AI Agents, by Resham Joshi
View PDF<br>HTML (experimental)
Abstract:AI agents that persist across sessions need memory they can retrieve, audit, update, and erase. Existing memory systems often collapse source evidence, extracted facts, retrieved context, and answer policy into one opaque prompt path, making failures difficult to diagnose: a wrong answer may come from missing evidence, unsupported extraction, stale state, retrieval loss, or answer-model behavior. We present Eywa, a provenance-grounded memory architecture built around evidence before belief. Eywa stores immutable source evidence before deriving canonical facts, validates extracted memories against typed signals and source support, and retrieves bounded memory context through a deterministic multi-route read path with zero LLM calls inside retrieval. Retrieved context is returned separately from answer instructions, allowing the same memory substrate to be evaluated across frontier, budget, and local answer models. Under a frozen, artifact-recorded retrieval configuration, Eywa reaches 90.19% judge accuracy on the LoCoMo C1-C4 split with Claude Sonnet 4.6 write and QA roles. On LongMemEval-S, it reaches 88.2% retrieval-sufficiency accuracy. On BEAM, a 700-question technical-memory stress benchmark, it reaches 81.45% mean nugget score and 85.29% pass@score >= 0.5. Full per-question artifacts, including questions, gold answers, model answers, retrieved context, and labels, are published at this https URL.
Comments:<br>29 pages, 3 figures, 16 tables. Benchmark artifacts available at this https URL
Subjects:
Computation and Language (cs.CL)
Cite as:<br>arXiv:2605.30771 [cs.CL]
(or<br>arXiv:2605.30771v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.30771
Focus to learn more
arXiv-issued DOI via DataCite
Submission history<br>From: Resham Joshi [view email]<br>[v1]<br>Fri, 29 May 2026 02:56:35 UTC (3,432 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled Eywa: Provenance-Grounded Long-Term Memory for AI Agents, by Resham Joshi<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.CL
next >
new<br>recent<br>| 2026-05
Change to browse by:
cs
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
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 .
Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)