Paper Detail

Living Context Graphs: Continual Semantic Learning for Enterprise Data Reasoning

Varun Agrawal, Ayush Srivastava, Eshan Gujar, Kaushal Kumar, Ayush Gupta

arxiv Score 14.3

Published 2026-11-16 · First seen 2026-11-17

General AI

Abstract

Enterprise AI can now perform analytics, reporting, and data-driven workflows, yet the data foundations it relies on remain hard to operationalize: business meaning, relationships, metric definitions, and reporting conventions are absent from database schemas and scattered across undocumented systems and tribal knowledge. We introduce the Living Context Graph (LCG), a continually learned context layer that makes existing enterprise data operational for AI without requiring a copy or transformation of the underlying warehouse. LCG bootstraps base semantics and relationships from the data itself, builds a concept graph that indexes business context as queries are served, writes durable semantic learnings from verified outcomes, and withdraws or re-earns context when later outcomes contradict prior routes. We evaluate LCG through text-to-SQL, a core data-reasoning task, on a transfer-aware split of three BIRD databases comprising 499 questions: 353 form the learning history and 146 are held out and never used to update the context layer. Bootstrapping alone improves overall accuracy by +4.6 percentage points. Learning only from the history raises accuracy on the untouched held-out transfer set by +22.6 points (95% CI [+14.4, +30.8]), exceeding five-shot retrieval from the same history by +12.3 points. Incremental learning reaches the one-shot endpoint within observed evaluation noise on every database. Ablating the graph changes held-out accuracy by at most one question per database but increases per-query cost 2.3-3.3x and median latency 1.8-3.4x: continually learned semantics drive accuracy, while the graph makes that context efficient to serve.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{agrawal2026living,
  title = {Living Context Graphs: Continual Semantic Learning for Enterprise Data Reasoning},
  author = {Varun Agrawal and Ayush Srivastava and Eshan Gujar and Kaushal Kumar and Ayush Gupta},
  year = {2026},
  abstract = {Enterprise AI can now perform analytics, reporting, and data-driven workflows, yet the data foundations it relies on remain hard to operationalize: business meaning, relationships, metric definitions, and reporting conventions are absent from database schemas and scattered across undocumented systems and tribal knowledge. We introduce the Living Context Graph (LCG), a continually learned context layer that makes existing enterprise data operational for AI without requiring a copy or transformati},
  url = {https://arxiv.org/abs/2611.20976},
  keywords = {cs.CL, cs.AI, cs.DB, cs.ET, cs.IR},
  eprint = {2611.20976},
  archiveprefix = {arXiv},
}

Metadata

{}