Preprints and disclosures.

Field-Theoretic Memory for AI Agents

Continuous Dynamics for Context Preservation

A memory architecture treating stored information as continuous fields governed by partial differential equations — semantic diffusion, thermodynamic decay, and field coupling for persistent, composable agent memory.

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

Semantic MAP-Elites red-teaming across frontier LLMs

A quality-diversity evolutionary framework that red-teams LLMs at the semantic level — evolving interpretable attack strategies (not token sequences) and using a MAP-Elites archive to illuminate distinct vulnerability profiles across GPT-4o-mini, Claude 3.5 Sonnet, Gemini 2.0 Flash, and an open-weight model. The contribution is an interpretable, reproducible baseline a safety team can triage and defend against.

Verity: Neuro-Symbolic Synthesis of Verified Distributed Systems

CE2P translates formal-verification failures into structured LLM feedback. The benefit is inversely correlated with model capability — weaker models gain the most.

Trust-Based Decision Routing

A formal framework for ROI-based decision routing in multi-tier verification systems.

Attack Taxonomy for Agentic AI Systems

A comprehensive threat model covering input, state, tool, planning, and coordination attacks, with empirical evaluation across agent architectures.

Activation-Based Attack Detection for Autonomous Agents

Interpretability methods to detect adversarial attacks on agentic systems — extending metacognitive probing to security.

Calibrated Uncertainty in LLM Reasoning Chains

Uncertainty quantification that tracks actual accuracy — activation-based estimation and propagation through multi-step reasoning chains.