An automatically generated digest of the newest public records curated into ARCS. Descriptions are derived from depositor-supplied Zenodo metadata; the digest does not add peer-review claims or independent capability judgments.
Preprint · 2026-08-27
Allit, Gabriel
Persistent state is often credited as memory or learning even when it never affects a later decision. This preprint introduces Persistent Cognitive Influence (PCI), an operational evaluation discipline that separates recording, durable persistence, fresh-process retrieval or reload, canonical cognitive consumption, attributable downstream influence…
Archive record ↗
Preprint · 2026-08-25
Allit, Gabriel
Autonomous AI systems increasingly require external capabilities that are not economically or operationally sensible to bundle into a single model or runtime. Model Context Protocol (MCP) standardizes capability discovery and invocation, while x402 standardizes HTTP-native payment negotiation for machine actors. Those protocols solve important…
Archive record ↗
Working paper · 2026-08-15
Allit, Gabriel
This working paper describes a systems pattern implemented in EvoMind for converting a high-level user objective into one or more real, verified work products without granting the planner direct execution authority. The pattern separates semantic planning, capability resolution, governance admission, execution, independent verification, and artifact-state…
Archive record ↗
Preprint · 2026-08-10
Allit, Gabriel
EvoMind is a local-first, governed cognitive runtime investigating whether deployment experience can become persistent, reusable, transferable operational capability. Evaluating EvoMind against the contemporary artificial-intelligence landscape requires more than comparing parameter counts, language benchmarks, multimodal inputs, computer use, persistent…
Archive record ↗
Technical note · 2026-08-10
Allit, Gabriel
EvoMind is a local-first, governed cognitive architecture designed to separate cognitive capability, runtime authorization, execution, and verification into explicit system authorities rather than treating model output as direct permission to act. This technical note documents EvoMind at a frozen first-party engineering snapshot dated 10 August 2026…
Archive record ↗
Working paper · 2026-07-08
Allit, Gabriel
Tool-using AI agents increasingly operate in asynchronous, partially observable environments where a successful API return, mouse click, keystroke sequence, or tool invocation does not guarantee that the intended semantic outcome occurred. This white paper proposes Verified Semantic Transitions (VST), an implementation-neutral architectural primitive that…
Archive record ↗
Preprint · 2026-06-06
Allit, Gabriel
EvoMind is a governed cognitive architecture and research platform for autonomous reasoning, memory, planning, learning, and desktop-agent execution. The architecture is organized around a closed-loop cognitive cycle consisting of perception, world-model maintenance, memory formation and retrieval, decision support, planning, governance enforcement…
Archive record ↗
Contribute to ARCS. Relevant papers, preprints, software, datasets, benchmarks, protocols, replication work, and well-documented negative results are welcome for curator review through the Zenodo community.