Research

Calibrated multi-agent decision systems for high-stakes automation.

My PhD is about one question: how do you trust the output of an autonomous agent? The answer I work on is a proposer, challenger, judge architecture, where independent agents argue and adjudicate before a decision is acted on. The same chassis I study academically is the safety layer I deploy in real systems (OC1, OC2, MVF-Composer).

The thread

One architecture, four systems, one paper trail

Proposer, Challenger, Judge - a trust chassis for autonomous agents

The single-LLM-call pattern is convenient and dangerous: convenience because it is one prompt, dangerous because the verifier is the same model that produced the claim. My dissertation develops a multi-agent pattern where a Proposer drafts a decision, a Challenger attacks it, and a Judge commits a verdict. The transcript is hashed and committed externally, so the audit trail is outside the LLM rather than inside it.

The pattern shows up in three deployed systems (OC1, OC2, MVF-Composer) and in the IEEE ICBC 2026 paper on stablecoin reserve control. I treat the engineering and the research as the same feedback loop: I ship the system, instrument it, find the failure mode the paper didn't predict, and ship the next paper.

Themes: multi-agent systems, consensus and trust, calibrated forecasting, blockchain and decentralized-system safety.

PROPOSER drafts a decision CHALLENGER attacks the decision JUDGE commits a verdict EXTERNAL receipt / on-chain HUMAN review on flag plan critique commit flag
PhDComputer Science, University of Notre Dame
AdvisorProf. Jarek Nabrzyski
Timeline2020 to 2026 (expected)
TopicTrust and systemic risk in decentralized systems; multi-agent architectures for calibrated, safety-aware automation
Core methodAdversarial multi-agent debate, cryptographic transcript receipt, block-by-block crisis replay, formal safety specification
Applied inOC1 (agent safety), OC2 (DeFi debate), MVF-Composer (stablecoin control)
Research themes

What I work on

01

Multi-agent consensus

Patterns where independent agents argue, judge, and commit a decision outside the LLM that drafted it.

02

Calibrated automation

Decisions the system can defend with a measurable confidence score and a human-readable audit trail.

03

Stablecoin safety

Defense mechanisms for the moments when a stablecoin depegs, replayed block by block against real crises.

04

Trust in decentralized systems

Why trust assumptions break, when cryptography helps, and when you still need a human in the loop.

Publications

Peer-reviewed work

Four publications, single-author first author on the most recent, an invited talk at IEEE ICBC 2026.

2026

Hybrid Stabilization Protocol for Cross-Chain Digital Assets Using Adaptor Signatures and AI-Driven Arbitrage

Book chapter · You, Kuehlkamp, Nabrzyski · DOI: 10.1007/978-3-032-00495-6_8

2024

Persona-Preserving Reputation Protocol (P2RP) for Enhanced Security, Privacy, and Trust in Blockchain Oracles

Cluster Computing (journal) · You, Radivojevic, Nabrzyski, Brenner · DOI: 10.1007/s10586-023-04222-4

2023

Mining User Behavior in Decentralized Applications for Blockchain Trust and Security Analytics

IEEE BCCA 2023 · You, Joshi, Kuehlkamp, Nabrzyski · DOI: 10.1109/bcca58897.2023.10338860

2022

Trust in the Context of Blockchain Applications

IEEE BCCA 2022 · You, Radivojevic, Nabrzyski, Brenner · DOI: 10.1109/bcca55292.2022.9922068

Where the work has appeared

2026
IEEE ICBC 2026 · MVF-Composer talk
Conference speaker
2026
InnoAI Thailand 2026 · stablecoin and agent safety
Invited speaker
2024
Cluster Computing (journal)
First author
2023
IEEE BCCA 2023
First author
2022
IEEE BCCA 2022
First author
2020
Hyperledger Global Forum 2020
Speaker
2020
Techstars Seattle Blockchain Startup Weekend
First place
2025
Sino-German Scientist Conference 2025
Session host
Academic history

Where I trained

PhD

Computer Science

University of Notre Dame · 2020 to 2026 (expected)
Advisor: Jarek Nabrzyski

MS

Computer Science (Information Security)

Purdue University · 2018 to 2019

BA

Mathematics

University of Washington · 2014 to 2018

Want a copy of a paper or a deeper walkthrough?

Happy to share preprints, code, and replication notes under standard academic terms. I read every message.