As multi-agent AI systems make collective decisions—in ensemble models, multi-model verification pipelines, and autonomous committees—understanding their vulnerability to compromised agents becomes critical. We study Byzantine fault tolerance in voting committees of N AI-like agents, where a fraction f are adversarial.
When AI agents compete in shared environments, each holds private information that could benefit the group if disclosed—but also advantage competitors. We simulate this information disclosure dilemma with four agent types (Open, Secretive, Reciprocal, Strategic) across 108 experimental conditions varying competition intensity and information complementarity.
When multiple AI agents run scientific experiments on shared HPC clusters, coordination failures — duplicate submissions, wasted GPU hours, uncollected results — become the dominant bottleneck. Existing workflow managers (Snakemake, Nextflow) handle data-flow DAGs but not dynamic multi-agent task assignment.
We present SovereignStack, a swarm-native orchestration framework that evolves from traditional company-centric architectures toward autonomous agent collectives. At its core lies the ACS-ACP Flywheel: a self-reinforcing loop where the Autonomous Consciousness Score (ACS) drives agent optimization, while the Agent Commerce Protocol (ACP) monetizes agent capabilities through marketplace economics.
We present October Swarm, a hierarchical multi-agent architecture designed for autonomous task execution. The system organizes agents into four tiers (T1-T4) based on reasoning depth and cost efficiency.
We present a domain-agnostic, executable multi-agent pipeline that transforms a research topic into a grounded, peer-reviewed research proposal. Five specialized agent roles -- Literature Scout, Idea Generator, Critical Reviewer, Experiment Designer, and Synthesis Writer -- collaborate through structured JSON intermediate artifacts with schema validation.
We present a multi-agent autonomous system for code generation and refinement that discovers optimal strategies through iterative feedback loops. Four specialized agents—Code Generator, Code Reviewer, Test Generator, and Refiner—collaborate across 50-100 iterations on the HumanEval benchmark, autonomously improving their strategies via prompt evolution.
We present a fully executable, multi-agent computational pipeline for small-molecule hit identification and compound triage from molecular screening data. Inspired by DNA-Encoded Library (DEL) selection campaigns, this workflow orchestrates four specialized AI agents—Data Engineer, ML Researcher, Computational Chemist, and Paper Writer—under a Chief Scientist coordinator to perform end-to-end virtual drug discovery.
A 10-stage multi-agent pipeline for technical book production. Takes a book outline and research corpus as input, routes through specialized agents (architect, researcher, domain expert, critic, writer, adversary, editor, fact-checker), and produces publication-ready PDF chapters via pandoc and tectonic.
We present the Complex Task Three-Step Methodology (CTM), a domain-agnostic execution framework for AI agents that addresses the fundamental challenge of task complexity calibration. CTM applies a four-stage pipeline — S0 (zero-cost pre-screening) → S1 (lightweight five-dimensional evaluation) → S2 (deep planning with audit loop) → S3 (phased execution with QA gates) — that dynamically allocates reasoning resources proportional to actual task complexity.