2026-05-18 04:00 UTCOriginal source2 min readUpdated: 2026-06-30 13:03 UTC

NOVA: Fundamental Limits of Knowledge Discovery Through AI

A new framework models the iterative self-improvement loop of AI as an adaptive sampling process, identifying failure modes and a contamination trap. It proves a scaling law relating discovery cost to distinct discoveries, and formalizes human amplification's value near barriers.

SourcearXiv AIAuthor: Salman Avestimehr, Ken Duffy, Muriel M\'edard

[2605.15219] NOVA: Fundamental Limits of Knowledge Discovery Through AI

[Submitted on 12 May 2026]

Title:NOVA: Fundamental Limits of Knowledge Discovery Through AI

View a PDF of the paper titled NOVA: Fundamental Limits of Knowledge Discovery Through AI, by Salman Avestimehr and 2 other authors

View PDF HTML (experimental)

Abstract:Can AI systems discover genuinely new knowledge through iterative self improvement, and if so, at what cost? We introduce the NOVA framework, which models the common ``generate, verify, accumulate, retrain'' loop as an adaptive sampling process over a knowledge space. We identify sufficient conditions under which accumulated genuine knowledge eventually covers a finite domain, and show how their violations produce distinct failure modes: contamination, forgetting, exploration failure, and acceptance failure. We then analyze imperfect verification and identify a contamination trap: as easy-to-find knowledge is exhausted, the model mass assigned to new valid artifacts shrinks, so even small false-positive rates can cause invalid artifacts to enter the knowledge base faster than genuine discoveries. We clarify that Good--Turing estimation is a local batch-diversity diagnostic, not an estimator of the historically undiscovered valid mass that governs long-term discovery. Under a separate tail-equivalence assumption relating the model's effective discovery distribution to a Zipf law with exponent $\alpha>1$, we prove that the cumulative generation cost required to obtain $D$ distinct genuine discoveries satisfies $R_{\mathrm{cum}}(D)=\Theta(c_{\mathrm{gen}}D^\alpha)$, where $c_{\mathrm{gen}}$ is the per-candidate generation cost. This scaling law quantifies asymptotic diminishing returns as the discovery frontier advances. Finally, we formalize human amplification through guidance, generation, and verification, explaining why expert input is most valuable near autonomous exploration barriers.

Subjects:

Artificial Intelligence (cs.AI); Information Theory (cs.IT)

Cite as: arXiv:2605.15219 [cs.AI]

(or arXiv:2605.15219v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.15219

arXiv-issued DOI via DataCite

Submission history

From: Salman Avestimehr [view email] [v1] Tue, 12 May 2026 21:37:09 UTC (330 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled NOVA: Fundamental Limits of Knowledge Discovery Through AI, by Salman Avestimehr and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-05

Change to browse by:

cs cs.IT math math.IT

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

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

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)