Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems: An Information-Controlled Empirical Study on Prediction Markets
Maksym Nechepurenko, Pavel Shuvalov · 2026 · arXiv preprint
PDF · arXiv · SSRN · DOI · Code
We study how prediction market rules — resolution typology, oracle design, and trading constraints — affect price accuracy, manipulation resistance, and the quality of the information aggregated.
A prediction market is only as good as its rules. The resolution mechanism determines whether prices reflect genuine beliefs or strategic manipulation. The oracle design determines who can influence outcomes and at what cost. The fee structure determines who participates.
These are mechanism design questions with real stakes: misconfigured markets have cost participants money and eroded trust in the whole asset class. Getting the mechanism right is not merely academic.
Maksym Nechepurenko, Pavel Shuvalov · 2026 · arXiv preprint
PDF · arXiv · SSRN · DOI · Code
Maksym Nechepurenko, Pavel Shuvalov · 2026 · Working Paper
PDF · arXiv · SSRN · Code
Maksym Nechepurenko · 2026 · Working Paper
arXiv · SSRN · DOI · Code
Maksym Nechepurenko · 2026 · Working Paper
PDF · arXiv · SSRN · DOI
A curated validation set mapping eight publicly documented episodes of suspected informed trading on Polymarket to concrete on-chain market identifiers. Cases span 2023–2026 and cover 24 individual markets across military and geopolitical actions, corporate proprietary disclosures, and regulatory decisions.