Skip to content
Publications

Pioneering
AI research.

We regularly publish our architectural discoveries, alignment methodologies, and agent benchmarks to help foster an open and verifiably safe intelligence ecosystem.

Model Architecture
April 2026

Vilcus-1: Multi-Step Inference Chains via Curated Rationales

Elena Rostova, Marcus Thorne, Alok Mehta

We introduce Vilcus-1, a proprietary reasoning model trained to build dense logical rationales prior to emitting terminal tokens. By formulating logical search as a discrete optimization process, we show significant reasoning consistency gains over standard autoregressive decoding.

Safety & Alignment
February 2026

Zero-Hallucination Alignment via Verified Formal Proofs

Amara Okoye, Elena Rostova

This paper presents a scalable methodology to enforce structural alignment in large language models by feeding formally verified proof solvers directly into the reward modeling objective. We demonstrate a reduction in critical factual errors without degradation in open-ended generative speed.

Autonomous Agents
December 2025

Cordenex: Autonomous Code Synthesizers with Closed-Loop Execution

Devon Chen, Liam Vance

We detail Cordenex, an autonomous coding agent that utilizes a dedicated compiler feedback environment during inference to self-correct compilation and logical errors before finalized code generation. We evaluate its capabilities on highly complex long-horizon engineering tasks.