Publications
Forthcoming work and cited prior art.
Phase I deliverables will be submitted to peer-reviewed venues. Where commercially compatible, the evaluation harnesses and reference implementations will be open-sourced as research artifacts.
Forthcoming · in progress
Three planned publications, one per open problem.
Stateful sub-second cold-start for per-tenant agent microVMs
Forthcoming · target: USENIX ATC
Empirical characterization of stateful Firecracker microVM cold-start under SMB workload patterns; snapshot-restore + delta-hydration measurements at 1k restorations p95 < 800 ms target.
A runtime supervisor for emergent coordination failure in multi-agent LLM systems
Forthcoming · target: NeurIPS Safety / IEEE S&P
200-scenario evaluation harness for multi-agent action-conflict detection on production tool calls. Sub-200ms classifier with ≥90% precision target. Open-sourced harness and dataset.
Operator-readable cryptographic audit chains for autonomous AI in small business
Forthcoming · target: CHI / USENIX Security
Reference implementation of Merkle-anchored per-action event records with deterministic prose rendering. Usability study with 12 SMB owner-operators; planted-error identification rate.
Bibliography
Cited prior art our research builds on.
Firecracker: Lightweight Virtualization for Serverless Applications
Agache et al. · NSDI 2020
The microVM substrate underlying Problem 1.
Faasm: Lightweight Isolation for Efficient Stateful Serverless Computing
Shillaker & Pietzuch · USENIX ATC 2020
Stateful serverless isolation lineage.
Catalyzer: Sub-millisecond Startup for Serverless Computing with Initialization-less Booting
Du et al. · ASPLOS 2020
Snapshot-restore lineage we extend to stateful agents.
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Wu et al. · 2023
Multi-agent LLM systems baseline; measures task success but not coordination safety.
Constitutional AI: Harmlessness from AI Feedback
Bai et al. · 2022
Single-agent guardrail lineage; we extend to coordinated multi-agent case.
The Off-Switch Game
Hadfield-Menell et al. · 2017
Corrigibility theory — formal frame we extend empirically.
Cooperative Inverse Reinforcement Learning
Hadfield-Menell et al. · 2016
Game-theoretic frame for inter-agent coordination.
Certificate Transparency
Laurie et al. · RFC 6962
Public hash-chained log lineage underlying Problem 3.
Practical Byzantine Fault Tolerance
Castro & Liskov · 1999
Tamper-evidence heritage for the audit chain.
Concerning Trustworthy AI: A Computational Perspective
Liu et al. · 2022
Trustworthy-AI survey we extend at the SMB-platform layer.