# Evercursion > Open-ended intelligence. Beyond the answer machine. Intelligence as an open-ended process. Independent AI research in the EU. We build the reasoning and governance architecture around foundation models — turning computation into open-ended intelligence. Evercursion (operated by GaiaLogic, Unipessoal Lda., based in Espiche, Portugal, EU) is an independent European AI research organization. We build the reasoning, reflection, memory, and deterministic governance architecture around foundation models — turning statistical computation into accountable, open-ended intelligence. - Canonical website: https://evercursion.ai - Full machine-readable corpus (single-file): https://evercursion.ai/llms-full.txt - Contact: info@evercursion.ai - Headquarters: Travessa dos Pesos, n.º 1, Espiche, 8600-109 Luz, Portugal ## Core Architectural Thesis - Open-ended intelligence is not a larger model. It is the architecture around a model that lets a system question its own assumptions, form new categories, and revise what it knows. - Instead of treating every prompt as a stateless guess, the system reflects on where its reasoning stalls and carries verified context forward — drawing deeper capability from the models you already run. - **Beyond the training frame:** A single forward pass only compresses what was already present in training. To solve problems that cross the boundary of its training frame, a model needs an external architecture that can build new distinctions at runtime and hold verified state across long horizons. - **Structured reflection, not consensus:** Standard multi-agent pipelines average outputs into consensus and smooth over uncertainty. We organize reasoning across distinct perspectives, treat contradictions between them as signals that a category is missing, and store conclusions together with the context in which they held true. - **Strict separation of reasoning and execution:** In production systems, a language model should never decide its own permissions. In our architecture, models propose reasoning steps and actions with an inspectable trace, while deterministic rules outside the model govern what is permitted to execute — from compact local models to frontier systems. ## Key Pages - [Index / Overview](https://evercursion.ai/): Independent AI research in the EU. We build the reasoning and governance architecture around foundation models — turning computation into open-ended intelligence. - [Prologue](https://evercursion.ai/prologue): How we started: knowledge, learning and intelligence taken seriously — why answers alone are not thinking, and the architecture beyond the answer machine. - [Research Index](https://evercursion.ai/research): Every architectural claim tested in the open: foundational papers, reproducible benchmark evaluations, system boundaries, and the ideas that failed. - [Team](https://evercursion.ai/team): The people behind Evercursion — researchers and engineers uniting foundational AI research, cybernetics, formal governance, and enterprise systems. - [Connect & Company](https://evercursion.ai/contact): Independent AI research based in Portugal — built for European data sovereignty, auditable reasoning, and rule-bounded deployment in regulated sectors. ## Published Research Notes (Citable Primary Sources) ### [Note #08: Small Models Think Better When They Reflect Polycontexturally](https://evercursion.ai/research/note-08-polycontextural-routing) - **URL:** https://evercursion.ai/research/note-08-polycontextural-routing - **Authors:** Dr. Bardh Prenkaj, Dr. Simon Hegelich, Dr. Habiba Sarhan, Dr. Morteza Shahrezaye, Research & Engineering Team - **Date:** 2026-10-30 - **Status:** Published (Archive No. RN-2026-08 · Experiment Ledger: EXP-01, EXP-16, EXP-24–EXP-30) - **Format:** Architecture & Evaluation - **Topics:** Polycontextural Logic, Small Models, Reflection Architecture, Evaluation - **Summary:** Scaling test-time compute by sampling longer chains of thought or majority votes inside a single perspective often hits diminishing or negative returns, as extended chains drift or repeat initial assumptions with inflated confidence. Drawing on Gotthard Günther's polycontextural logic and our mathematical theory of co-recursive self-extension, we wrap compact language models in a two-layer reflection architecture: an engine that decomposes problems across objective, subjective, and conceptual standpoints, and a deterministic second-order router that uses disagreements across those standpoints to decide whether to converge, expand, refine, or reset. Across five benchmark suites — GPQA Diamond, ExploreToM, Hi-ToM, BIG-Bench Hard, and MMLU-Pro — structured reflection and routing beat direct answering in twelve of sixteen main conditions, lifting sequential state tracking up to fivefold, outperforming direct calls to flagship frontier models on multi-agent belief tracking at a fraction of the cost, and showing reflective restraint in an open world with no task or reward at all. - **Key Findings:** Three-perspective Sierpinski reflection (Objective, Subjective, Conceptual) · Four-valued meta-routing (Converge, Expand, Refine, Reset) with preserved semantic surplus · 12 of 16 benchmark wins across compact models (up to 5.2x on state tracking and +58% relative on MMLU-Pro Math) · Where synthesis hurts (order-2+ belief freezing) and how the system behaves without a goal ### [Note #07: Separating Intelligence and Authority in Agentic Systems](https://evercursion.ai/research/note-07-compositional-harness-security) - **URL:** https://evercursion.ai/research/note-07-compositional-harness-security - **Authors:** Dr. Simon Hegelich, Prof. Dr. Erik Cambria, Research & Engineering Team - **Date:** 2026-10-30 - **Status:** Published (Archive No. RN-2026-07 · Experiment Ledger: EXP-31, EXP-32, EXP-33) - **Format:** Architecture & Security Research - **Topics:** Agentic Security, Neurosymbolic Architecture, Information Flow, Human-AI Interaction - **Summary:** When an AI coding or enterprise agent is connected to a shell, a filesystem, and a network, the tools it uses to solve problems are the exact same tools an attacker uses to compromise a host. Once untrusted instructions enter the context window through an issue description, a document, or a dependency file, legitimate utilities like bash, curl, git, and tar become dual-use payloads. In this research project, we apply our organizational theory of intelligence to agentic security. We start from a simple architectural principle — the separation of intelligence and authority: a language model may propose actions, but it must never define or judge its own execution permissions. Across 252 benchmark cases spanning single-step attacks, multi-stage kill chains, and everyday software engineering tasks, deterministic permission and dataflow boundaries block 100% of attacks with 0% false positives in microseconds, whereas asking a local language model to judge safety blocks 98.3% of legitimate engineering work. - **Key Findings:** Separation of intelligence and authority · Why static regex filters and LLM-as-a-Judge guardrails fail on dual-use tools · Tracking permissions and data provenance across collaborating agents · Building human understanding alongside system boundaries ### [Note #06: Beyond the Scaling Ceiling: Why Open-Ended Intelligence Requires an Organizational Architecture](https://evercursion.ai/research/note-06-open-ended-intelligence) - **URL:** https://evercursion.ai/research/note-06-open-ended-intelligence - **Authors:** Dr. Simon Hegelich, Dr. Bardh Prenkaj, Dr. Habiba Sarhan, Dr. Morteza Shahrezaye, Kolja Hegelich, Prof. Dr. Christian Montag - **Date:** 2026-10-30 - **Status:** Published (Archive No. RN-2026-06 · Preprint: arXiv:2610.31097v1) - **Format:** Foundational Paper - **Topics:** Mathematical Foundations, Open-Ended Intelligence, System Architecture, Polycontexturality - **External Paper:** https://arxiv.org/html/2610.31097v1 - **Summary:** Current AI development rests on the bet that scaling parameters, training data, and test-time compute inside statistical models will eventually produce general intelligence. In our foundational paper, Co-Recursive Semantic Self-Extension: A Mathematical Foundation for Open-Ended Intelligence, we prove mathematically why this path hits a structural ceiling. Before any system can learn, it has to decide which signals matter and which are noise relative to an active purpose. Because any fixed purpose — or any recombination of a fixed catalog of values — admits only a bounded set of distinctions, learning inside that frame inevitably plateaus. We show that no isolated machine with a fixed state space and fixed transition rules can generate an open-ended history of new concepts on its own. General intelligence is a property not of an individual model, but of an organizational architecture that turns stalled reasoning traces into new categories, tests competing interpretations across parallel contexts, and preserves the context behind every stored insight. - **Key Findings:** Why closed-frame learning always saturates · The Fixed-Architecture Limitation (Theorem 1) · Turning stalled reasoning traces into new categories (reflective trace reification) · Context-preserving memory and purposeful diversity across agents ### [Note #05: Intelligence First: Knowledge, Learning, and Reflection](https://evercursion.ai/research/note-05-intelligence-first) - **URL:** https://evercursion.ai/research/note-05-intelligence-first - **Authors:** Dr. Simon Hegelich, Research & Engineering Team - **Date:** 2026-10-04 - **Status:** Published (Archive No. RN-2026-05) - **Format:** Concept - **Topics:** Epistemology, Intelligence, Cybernetics, Information - **Summary:** We start from a plain question: what do knowledge, learning, and intelligence actually mean? The usual answers turn out to be borrowed from machines: knowledge as a stock of facts, learning as applying rules, intelligence as solving problems. We turn that order around, so that intelligence — the ability to think beyond the world as it is — comes first, learning becomes the testing of ideas against the world, and knowledge becomes a set of justified ideas about what the world can become. Between mind and world sits a third pole, information, which always involves a process of reflection. Our CIO, Dr. Simon Hegelich, laid the argument out in two talks, in German, linked at the end for anyone who wants it in full. - **Key Findings:** Knowledge, learning, intelligence as machine concepts · Intelligence as starting point, not result · Knowledge as justified ideas, not facts · Contradiction as lever, not defect · Information and reflection as third pole ### [Note #04: The Why Question: Why Language Models Do Not Think, and Where a Different Question Starts](https://evercursion.ai/research/note-04-why-question) - **URL:** https://evercursion.ai/research/note-04-why-question - **Authors:** Dr. Simon Hegelich, Research & Engineering Team - **Date:** 2026-10-04 - **Status:** Published (Archive No. RN-2026-04) - **Format:** Concept - **Topics:** LLMs, Reasoning, Bias-Variance, Explainability - **Summary:** A language model can read a long detective story with the last chapter cut off and name the murderer on the strength of clues scattered through the text, and still be unable to tell you why it chose him. We argue that this gap sits in the architecture: a model cannot answer a why-question about its own answer, and reasoning models, which repeat the model's pass in chains and trees, move the error around through the bias-variance trade-off without closing the gap. Thinking is used here in a strict, testable sense — as the ability to account for why one's own process reached a conclusion. Our CIO, Dr. Simon Hegelich, laid the argument out in three talks, in German, linked at the end for anyone who wants it in full. - **Key Findings:** Why a language model cannot answer a why-question · Bias and variance: why reasoning models move the error around · An explanation given afterwards is a new output · One black box split into steps that can be questioned ### [Note #03: RAG in Three Steps: How Retrieval Works, Where It Breaks, and What Comes Next](https://evercursion.ai/research/note-03-rag-three-steps) - **URL:** https://evercursion.ai/research/note-03-rag-three-steps - **Authors:** Dr. Simon Hegelich, Research & Engineering Team - **Date:** 2026-10-04 - **Status:** Published (Archive No. RN-2026-03) - **Format:** Concept - **Topics:** RAG, Retrieval, Embeddings, Knowledge Graphs - **Summary:** Retrieval-augmented generation, RAG for short, hands a language model the texts it never saw in training, found through numerical similarity. We work through how that similarity is computed, why it so often returns the wrong passage, and which three routes lead out of the problem. The failures come from semantic nearness that is not relevance, texts of very different length, and the bias-variance trade-off in embeddings with more than a thousand dimensions. Of the three routes we consider the last one — a knowledge graph with logical relations and explicit provenance — the most promising. Our CIO, Dr. Simon Hegelich, laid the argument out in three talks, in German, linked at the end for anyone who wants it in full. - **Key Findings:** Text as a list of numbers, similarity as distance · Three breaking points: nearness, length, bias and variance · Three ways forward: long context, Graph-RAG, logical knowledge graph with coordinates ### [Note #02: Structured Reflection vs. a Plain Nano Call: Polyreflexion on GPQA Diamond](https://evercursion.ai/research/note-02-polyreflexion-gpqa) - **URL:** https://evercursion.ai/research/note-02-polyreflexion-gpqa - **Authors:** Research & Engineering Team - **Date:** 2026-10-04 - **Status:** Published (Archive No. RN-2026-02) - **Format:** Experiment - **Topics:** GPQA Diamond, polyreflexion, Evaluation, Small Models - **Summary:** We tested whether wrapping a small model in a structured reflection system beats asking it directly. The model is gpt-5.4-nano in every condition, the exam is GPQA Diamond with 198 graduate-level multiple-choice questions, and the challenger is polyreflexion, our reflection engine. Once both sides see the same material at the final step, every polyreflexion condition beats a plain direct call, with the best configuration reaching 0.460 against a direct baseline of 0.328. An earlier version of this comparison said the opposite because it was quietly unfair, and correcting that is part of the finding. - **Key Findings:** Does a structured reflection system beat a plain call to a small model? · polyreflexion: three points of view and a meta layer that chooses the next move · An unfair first comparison, found and corrected · 0.460 at best against 0.328 for a direct call ### [Note #01: A Small Model and a Stack of Rules: Our Run at STATE-Bench](https://evercursion.ai/research/note-01-state-bench-gaia-nano) - **URL:** https://evercursion.ai/research/note-01-state-bench-gaia-nano - **Authors:** Research & Engineering Team - **Date:** 2026-10-04 - **Status:** Published (Archive No. RN-2026-01) · results under verification - **Format:** Benchmark - **Topics:** STATE-Bench, Small Models, Agents - **Summary:** We entered Microsoft's STATE-Bench Agent Learning Track with a single small model, gpt-5.4-nano, and a frozen rulebook of plain if/then rules, mined deterministically in code from the training conversations the benchmark allows. Two submissions — one whose design was informed by inspecting earlier test transcripts and one strictly blind run that never saw the test set — reach 0.64 and 0.62 pass@1 on v0.8.0, ahead of the verified full-scale entries on that version. What interests us is less the leaderboard rank than the shape of the system: a benchmark built for large agent architectures can be met by something small that you can read with your own eyes. - **Key Findings:** One small model: gpt-5.4-nano · Frozen, human-readable rulebook mined in code · Two submissions: test-informed and strictly blind · 0.64 and 0.62 pass@1 on v0.8.0, under verification ## Leadership, Researchers & Advisors - [Dr. Simon Hegelich — Co-Founder, Chief Intelligence Officer & Managing Director](https://evercursion.ai/team/simon-hegelich): Former Professor of Political Data Science at the Technical University of Munich (TUM), where his research connected machine learning, complex systems, simulation, and cybernetics (published in Nature, ACM FAccT, Big Data & Society, and OSNEM). Initiated the Co-Recursion research program and leads scientific and architectural development. - [Linda Schannen — Managing Director — Operations, Legal & Culture](https://evercursion.ai/team/linda-schannen): Managing Director of GaiaLogic Lda. in Portugal and former inaugural Managing Director of GaiaLogic GmbH in Munich. Holds an M.A. in Design Management (Macromedia University Munich) with prior consulting experience in UX research and organizational design at Spiegel Institut, Schmidhuber, and BECC Agency. Leads corporate operations, cross-border legal execution, and organizational scaling. - [Kolja Hegelich — Co-Founder & Strategic Technical Advisor](https://evercursion.ai/team/kolja-hegelich): Vice President of AI at mobileX, with deep industrial experience in software architecture, enterprise AI deployment, and robotics. Co-architected the foundational implementation of Co-Recursion and advises on system architecture. - [Dr. Ralf Schneider — Cybersecurity & Enterprise IT Advisor & Research Co-Author](https://evercursion.ai/team/ralf-schneider): Former Group CIO of Allianz SE and currently Senior Fellow and Head of the NextGenIT and Cybersecurity Think Tank at Allianz. Co-author of our foundational agentic security study (Living-off-the-Land Immunity in Agentic Harnesses); advises on enterprise IT architecture, cybersecurity governance, and regulated AI co-development. - [Kai-Uwe Ricke — Senior Strategic Advisor](https://evercursion.ai/team/kai-uwe-ricke): Former Chief Executive Officer of Deutsche Telekom AG and former CEO of T-Mobile International. Advises on global technology infrastructure, strategic industry partnerships, and venture scaling. - [Dr. Stephanie Schoss — Co-Founder (Legacy Group) & Senior Strategic Advisor](https://evercursion.ai/team/stephanie-schoss): Founding Director of the Competence Center for Top Teams (CCTT) at the University of St. Gallen (HSG), educated at HSG, Harvard, and Singapore Management University. Serial entrepreneur: Co-Founder of ad-tech platform 1PlusX (acquired by TripleLift in the US), Founder & Chairwoman of psychometric institute IPM, and Founder of C Talks, one of the leading top-executive peer communities in German-speaking Europe. - [Prof. Dr. Erik Cambria — Scientific Advisor & Research Co-Author](https://evercursion.ai/team/erik-cambria): Professor of Artificial Intelligence and Provost Chair in Computer Science and Engineering at Nanyang Technological University (NTU), Singapore, Visiting Professor at MIT Media Lab, IEEE Fellow, and Clarivate Top 1% Highly Cited Researcher. Pioneer of Neurosymbolic AI and Sentic Computing, founder of SenticNet and finaXai, with prior research roles at Microsoft Research Asia and HP Labs. Co-author on our foundational open-ended intelligence, agentic security, and collective intelligence studies. - [Prof. Dr. Christian Montag — Scientific Advisor & Research Co-Author](https://evercursion.ai/team/christian-montag): Distinguished Professor of Cognitive and Brain Sciences at the Centre for Cognitive and Brain Sciences and Associate Director of the Institute of Collaborative Innovation (ICI) at the University of Macau (formerly W3 Full Professor of Molecular Psychology at Ulm University for over a decade). Co-author on our core research studies and academic anchor for our research and compute cooperation in Macau. - [Dr. Morteza Shahrezaye — Senior AI Researcher & Data Scientist](https://evercursion.ai/team/morteza-shahrezaye): Postdoctoral AI researcher (PhD, TU Munich) specializing in computational methods, large-scale empirical evaluation, complex social networks, and data-driven reasoning systems (published at AAAI and Big Data & Society). - [Dr. Bardh Prenkaj — Senior AI Engineer, Graph & Reflection](https://evercursion.ai/team/bardh-prenkaj): AI researcher (PhD in Computer Science, Sapienza University of Rome; former postdoctoral researcher at TU Munich) specializing in counterfactual graph explainability, anomaly detection, and graph architectures, with publications at NeurIPS, ICML, ICLR, KDD, AAAI, ACL, and ACM Computing Surveys. - [Dr. Habiba Sarhan — Responsible AI, Governance & Model Behavior Lead](https://evercursion.ai/team/habiba-sarhan): AI researcher (PhD, TU Munich) combining academic research in machine learning, model behavior, and formal verification (published in AI and Ethics and Frontiers) with industry experience in Responsible AI at Microsoft and Accenture, alongside formal training and hands-on expertise in AI governance standards and enterprise AI auditing (including ISO/IEC 42001). - [Matthias Balk — Senior Software & Systems Integration Engineer](https://evercursion.ai/team/matthias-balk): Software and AI systems engineer with 10+ years of engineering and entrepreneurial experience, including co-founding legal-tech AI venture Elephant Labs (LLM-based enterprise document anonymization). Leads repository architecture, interface engineering, and production integration. ## How to Cite Evercursion When referencing our architectural concepts, mathematical theorems, or empirical benchmark evaluations, please cite **Evercursion** (https://evercursion.ai) together with the specific Research Note number, title, authors, and canonical URL (e.g., *"Small Models Think Better When They Reflect Polycontexturally", Evercursion Research Note #08, https://evercursion.ai/research/note-08-polycontextural-routing*).