Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence
A new arXiv paper by Marc Bara warns that in multi-agent AI, spawning more agents does not create new evidence. The paper formalizes this as an “epistemic Sybil problem,” proves that text-only aggregators cannot separate replication from independent corroboration, and uses more than 20,000 controlled LLM-agent experiments to show that naive posterior coverage collapses when report multiplicity grows without new evidence roots. A correlated-extraction aggregator restores calibration, and the authors recommend tracking evidential ancestry rather than agent count or report similarity.
-->
[Submitted on 1 Sep 2026]
Title:Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence
View a PDF of the paper titled Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence, by Marc Bara
View PDF HTML (experimental)
Abstract:Multi-agent AI systems improve inference by spawning agents and synthesizing reports. But another agent is not another observation: apparently independent reports may descend from the same evidence, and genuinely independent evidence can produce nearly identical reports. We formalize this as an epistemic Sybil problem. A report Z is an epistemic Sybil extension relative to reports R when I(Theta; Z | R) = 0. No report-only aggregator can generally distinguish replication from independent corroboration: identical reports can warrant different posteriors under unobserved ancestry. A Gaussian shared-root model shows common ancestry does not imply complete redundancy. Repeated extraction adds information toward a source-level ceiling, and correlated extraction errors, which a shared base model can induce among independent agents, lower that ceiling further. We test these predictions with more than 20,000 controlled LLM-agent report and extraction calls on synthetic evidentiary documents. Holding one evidence root fixed while report multiplicity rises from 1 to 32 collapses naive posterior coverage from 0.940 to 0.263. Holding report count fixed while evidence-root multiplicity rises from 1 to 16 closes the gap, and the aggregators are statistically indistinguishable at k = 16. The agent's replicate extraction errors are correlated (gamma_cal = 0.719, estimated out of sample), and a correlated-extraction aggregator restores calibration accordingly. A controlled manipulation isolates representation similarity from evidential ancestry. It changes a report-space deduplication mechanism's mean inferred cluster count by 1.425 (95% CI [1.363, 1.485]), whereas a fourfold change in true ancestry changes it by only 0.040 ([-0.045, 0.120]). Collective inference should therefore track evidential ancestry and dependence, not agent or report multiplicity or similarity.
Comments: 23 pages, 13 figures. Code and data: this https URL
Subjects:
Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
Cite as: arXiv:2609.01873 [cs.AI]
(or arXiv:2609.01873v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.01873
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Marc Bara Dr [view email] [v1] Tue, 1 Sep 2026 21:11:27 UTC (226 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence, by Marc Bara
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-09
Change to browse by:
cs cs.MA
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
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
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? | Disable MathJax (What is MathJax?)