Open Access

AI-Forschung für Systeme mit Verantwortung

Artikel zu autonomen Agenten, regulierter Finanzwirtschaft, digitaler Identität, Ledgern, Energiemärkten, Bewertung, Bildung und Versicherung. Lesen Sie die neuesten Arbeiten und verfolgen Sie die Themen im Journal.

Zur Submission

SAIJ-5kdnql4rsq27Juli 2026

Jurisdiktionsübergreifende rechtliche Identitätssicherung für Capability Gating

Ein Design-Science-Vorschlag für gestufte, wiederverwendbare Identity Assurance natürlicher, juristischer und maschineller Entitäten

DOI 10.5281/zenodo.21901241

Walter Kurz

Swissi Institute for AI

Flache Maximalverifikation belastet alle Beteiligten mit dem seltensten Hochrisikofall. Dieses Modell trennt den Assurance-Zustand vom Capability Gate, das ihn nutzt. So folgt die Identitätsanforderung der Handlung und dem Gewicht ihrer Folgen, statt schon die blosse Teilnahme unnötig schwer zu machen.

Schlagwörter:

Identity Assurance
Capability Gating
gestufte und wiederverwendbare Verifikation
multi-jurisdiktionale Identität
data minimisation
Entitätstaxonomie
bitemporale Reliance
Design Science Research

SAIJ-zpd6gvtrfaunJuli 2026

Credentials und triangulierte Trust Signals auf einem einzelnen rechenschaftsfähigen Identifier

Ein Hash-verankertes Distributed-Ledger Framework für portable Identität über Jurisdiktionen hinweg

DOI 10.5281/zenodo.21901243

Walter Kurz

Swissi Institute for AI

Digitale Identität bleibt starr, solange sie an Provider Accounts, veränderliche Handles und lokale Wallet Schemes gebunden ist. Eine rechenschaftsfähige Hash-Anchor Tier liegt darüber: ein inerter Root Anchor, nicht verknüpfbare Profile Anchors für getrennte Kontexte und gate-spezifische Assurance zu einem Zeitpunkt.

Schlagwörter:

digitale Identität
verifiable credentials
rechenschaftsfähige Pseudonymität
distributed ledger
selective disclosure
Identity Assurance
self-sovereign identity
Hash Anchor

SAIJ-sh27g6sykt2kJuli 2026

Identity-Staked Consensus und Kollusionsresistenz in konzessionierten Validator Sets

Ein Trust Model für dezentrale und regelkonforme Distributed Settlement Infrastructure

DOI 10.5281/zenodo.21901245

Walter Kurz

Swissi Institute for AI

Permissioned Ledgers werden häufig als zentralisiert eingeordnet, weil Admission beschränkt ist. Die Trennung von Permissioning und Control Distribution macht Validator Identity zu extern kostspieligem Collateral: öffentliche Legal Identity, Charter State, Liability und Audit Exposure, mit affiliation-aware Voting Caps und Per-Member Collusion Margins.

Schlagwörter:

Identity-Staked Consensus
permissioned ledger
proof-of-authority
Validator Trust Model
Kollusionsresistenz
Settlement Infrastructure
Actor Assurance
Threshold Class Coverage
Ledger Evidence Record

SAIJ-f3jtignfyge3Mai 2026

Unternehmensbewertung, wenn AI das Geschäftsmodell prägt

Ein milestone-basiertes Real-Options Framework für das AI Valuation Uncertainty Problem

DOI 10.5281/zenodo.21901247

arXiv 2609.24181

Walter Kurz¹, Wojtek Stricker¹, Stefan Marx², Frank Reinhardt², Florian Kollberg²

¹Swissi Institute for AI²Hochschule für Wirtschaft und Umwelt Nürtingen-Geislingen

Discounted Cash Flow, der IDW-S-1-Ertragswertansatz und Market Multiples verdichten Milestone-Wahrscheinlichkeiten, Continuation Options und Risk Shifts zu undurchsichtigen Aggregatparametern. Ein milestone-gated Real-Options Overlay zerlegt diesen Wert in prüfbare Komponenten, wobei ein Success Readiness Index per-option Wahrscheinlichkeiten aus strukturierten Pairwise Comparisons ableitet.

Schlagwörter:

Unternehmensbewertung
AI Integration
Real Options
milestone-basierte Bewertung
intangible assets
AHP
multi-criteria decision analysis

SAIJ-cwo7xrcdsautMärz 2026

Funktionale Architektur europäischer Stromhandelsmärkte

Anforderungen an AI-gestützte Handelssysteme unter regulatorischen Restriktionen

DOI 10.5281/zenodo.21901249

Walter Kurz, Wojtek Stricker

Swissi Institute for AI

Der europäische Stromhandel läuft als restringiertes Mehrschichtsystem, in dem Rechtsarchitektur, Börsenmikrostruktur und Netzphysik über Forward-, Day-Ahead-, Intraday- und Balancing-Horizonte hinweg gemeinsam ausgeführt werden. Das Paper spezifiziert eine AI-gestützte Handelsarchitektur mit einem Permission Gate für ausführbare Aktionen und fail-closed Kontrolllogik unter REMIT, MiFID II, MiFIR und EMIR.

Schlagwörter:

EU-Strommarkt
Marktkopplung
NEMO-Topologie
Regelenergie
AI-Handelssysteme
Compliance-by-Design

SAIJ-xz3bi3q7fwimAug. 2025

Compliant AI Infrastructure für regulierte Finanzwirtschaft

Ein gestuftes Multi-Agenten-Framework mit DLT-Audit-Trails für Finanzoperationen im DACH-Raum

DOI 10.5281/zenodo.21901251

arXiv 2609.27632

Walter Kurz, Reinhard Magg

Swissi Institute for AI

Regulierung wird als Orientierungsschicht behandelt statt als deterministisches Regelwerk: Eine Matrix aus regulatorischer Intention und Exposure wird in konkrete Prohibitions, Obligations und Runtime Budgets kompiliert. Evidenz, Entscheidungen und Reason Codes binden an einen Permissioned DAG, sodass die Aufsicht nachvollziehen kann, wie ein Ergebnis zustande kam, und Fehler zurechnen kann.

Schlagwörter:

DACH-Finanzwesen
regulierte Finanzinstitute
Multi-Agenten-Expertensystem
policy-kompilierte Orchestrierung
Zielfunktion unter Restriktionen
Permissioned DLT
DAG-Timestamping
Audit Trails
EU AI Act
MiFID II
DORA
DSGVO
menschliche Aufsicht
Ausführungs-Gating
ESG-Budgets
Verifikation und Assurance

SAIJ-ddkjais6s332Aug. 2025

Ein regulierungskonformes AI- und Verifikationssystem für die Hochschulbildung unter ESG-konformen Restriktionen

DOI 10.5281/zenodo.21901253

Walter Kurz, Michel Malara, Wojtek Stricker

Swissi Institute for AI

Zwei verbundene Komponenten für die Hochschulbildung: ein rollenspezifisches Multi-Agenten-Framework für den institutionellen Betrieb und eine dezentrale Verifikationsschicht für Audit, Zeugnisauthentifizierung und manipulationsevidente Aufzeichnungen. DSGVO, EU AI Act, EQF, ECTS und ESG-Vorgaben sind als strukturelle Restriktionen kodiert statt nachträglich geprüft.

Schlagwörter:

Regulatory Technology
künstliche Intelligenz in der Bildung
Multi-Agenten-AI-Systeme
dezentrale Verifikation
akademische Tokenisierung
DSGVO-Compliance
EU AI Act
digitale Zeugnisinfrastruktur
ESG-Governance
UniAI
UniDVS

SAIJ-zkihhbpahsbrAug. 2025

Verifiable Federated AI Infrastructure

Schweizkonformes föderiertes AI-DLT-Netzwerk mit Nash-Gleichgewicht und ESG-Metriken

DOI 10.5281/zenodo.21901255

Walter Kurz, Michel Malara, Velimir Dedić

Swissi Institute for AI

Zentralisierte AI-Infrastruktur skaliert und kollidiert dabei mit Latenz-, Auditierbarkeits- und Energierestriktionen. Das Design trennt zentralisiertes Training von dezentraler Inferenz und Speicherung über fünf Knotenklassen und verbindet einen grössenneutralen Availability Floor mit gestuften Prämien für Servicelevel, ESG-Leistung und Antikonzentration.

Schlagwörter:

dezentrales Rechenzentrum
AI
Federated AI Infrastructure
ESG
ESG-bewusstes Compute
Nash-Gleichgewicht
digitale Souveränität
Schweizer Datenregulierung
tokenisierte Infrastruktur
verifizierbare AI-Dienste

SAIJ-soeptiqyucowAug. 2025

Generisches AI-DLT-Unternehmenssystem

Architektur und Methodik für skalierbare Domänenanpassung aus einem einheitlichen Kern-Framework

DOI 10.5281/zenodo.21901257

Walter Kurz, Michel Malara, Velimir Dedić

Swissi Institute for AI

Compliance wird in AI-Einsätzen meist nachträglich über Prompt Engineering hergestellt statt in der Grundlage verankert. Diese Architektur kodiert regulatorische, governancebezogene und ESG-Anforderungen als Problem des objective-under-constraints, sodass jeder spezialisierte Agent innerhalb rechtlich zulässiger und auditierbarer Grenzen arbeitet, bevor die Domänenarbeit beginnt.

Schlagwörter:

compliance-first AI
Multi-Agenten-Systeme
Distributed-Ledger-Technologie
gerichteter azyklischer Graph
Regulation by Design
ESG-Integration
domänenagnostische Architektur
deploymentagnostische Architektur
anbieteragnostische Architektur
objective-under-constraints

SAIJ-qzvrl4bwy7y2Mai 2025

Multi-Agenten-AI-Architektur für regulierte Versicherer

Ein generisches AI-Framework unter Solvency II und dem AI Act in Österreich und Deutschland

DOI 10.5281/zenodo.21901259

arXiv 2609.27636

Walter Kurz

Swissi Institute for AI

Der Versicherer wird als restringierte Optimierungseinheit unter Solvenz-, Rechts-, ESG- und Betriebsgrenzen modelliert und anschliessend in spezialisierte Agenten für Kapital, Underwriting, Schaden, Compliance und Betrugserkennung zerlegt. Human-in-the-Loop-Rollen kommen über gestufte Zugriffskontrolle hinzu, während ein Orchestrator die regulatorische Zulässigkeit über die gesamte Menge durchsetzt.

Schlagwörter:

Multi-Agenten-Systeme
Enterprise-AI
Versicherungsunternehmen
Solvency II
AI Act
regulierte Umgebungen
restringierte Optimierung
Prinzipal-Agent-Theorie
Nash-Gleichgewicht
Arrows Risikopoolbildung

Von arXiv

Aktuelle arXiv-Artikel

arXiv cs.AI

Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse

Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools. While prior research and benchmarks have studied about task success and task completion of these agentic systems, the research about agent to tool interaction, specifically in biology agentic workflow is limited. This...

arXiv cs.LG

The Drift Contract: Spectral Updates for Depth-Robust Local Learning

Local learning trains each layer with its own auxiliary loss and no global backward pass, which makes layer updates structurally parallel. Two problems have kept it marginal: accuracy degrades as depth grows, and hyperparameters are fragile. We apply Muon-style spectral update geometry (momentum orthogonalization...

arXiv cs.AI

Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity

Modern language-model agents are built around the agent loop, where the LLM is placed in an environment exposing a set of tools, and the LLM has full control over the workflow by alternating between tool calls and observing their output. However, certain workflows currently require additional engineering beyond the...

arXiv cs.LG

Signal2Symbol: Neuro-Symbolic Temporal Reasoning for Explainable Physiological Time-Series Anomaly Detection

Physiological time series such as electrocardiograms (ECG) and electroencephalograms (EEG) exhibit complex temporal structure, substantial acquisition variability, and a strong need for transparent decision-making. Although deep models can achieve high detection performance, they often provide limited insight into...

arXiv cs.AI

TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents

A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone does not justify intervention, because the replacement itself can introduce the very failure verification is meant to prevent. We introduce TwinCheck, an inference-time verification policy that considers...

arXiv cs.LG

HARN: Hierarchical Associative Resonance Network for Event-Driven Multi-Timeframe Forecasting

Financial time series evolve across multiple temporal resolutions, challenging forecasting systems to incorporate newly available information without repeatedly recomputing unchanged representations. We introduce HARN, a Hierarchical Associative Resonance Network for event-driven multi-timeframe forecasting. HARN...

arXiv cs.AI

Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations

The objective of this article is to provide design principles and a software architecture for enabling interaction between humans and multiple agents in simulated dynamic worlds. This connects the current era of general artificial intelligence (AI/AGI) with the proliferation of transformer-based conversational...

arXiv cs.LG

What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus

Frontier benchmarks need tasks that current models cannot solve. But a task that no model solves is not automatically a hard task. The same zero pass rate can come from a real capability gap, but it can also come from missing context, a broken reference solution, infrastructure failure, or a verifier that can be...

arXiv cs.AI

Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment

People hold diverse, sometimes conflicting values, so no single aligned model can satisfy everyone. Pluralistic alignment therefore calls for steerable models that can balance competing objectives differently. Multi-Objective Direct Preference Optimization (MODPO) does this by using an objective weight to span a...

arXiv cs.LG

LWCal: Loss-Weighted Calibration for Tabular Classifiers with Noisy Calibration Labels

Post-hoc probability calibration is usually evaluated under an optimistic assumption: the held-out calibration labels are clean. In many AI deployment settings, however, labels come from weak annotators, historical decisions, heuristics, or distant supervision, so the same label noise that corrupts training also...

arXiv cs.AI

Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution

Dependency conflicts in Python ecosystems arise from incompatible version constraints, missing packages, and undocumented compatibility relationships, causing many real-world code snippets to fail at execution. This paper presents PLLM+, a hybrid dependency-repair pipeline evaluated on the HG2.9K benchmark of 2,891...

arXiv cs.LG

A Leakage-Aware Multimodal Evaluation Framework for Early Intraoperative Acute Kidney Injury Prediction

Postoperative acute kidney injury (AKI) after major non-cardiac surgery carries substantial morbidity, yet early intraoperative risk stratification remains difficult. In this retrospective cohort study, we propose SynerT, a waveform-only hybrid temporal backbone that combines a causal dilated TCN with a hierarchy...

arXiv cs.AI

Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts

For multimodal large language models, when images or speech conflict with accompanying text, measured text reliance can entangle modality preference with evidence position. Earlier studies of text bias often used a fixed evidence order or moved task instructions with the evidence, leaving the contribution of order...

arXiv cs.LG

COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation

While Large Language Models (LLMs) have achieved remarkable results across various benchmarks, their alignment with normative values often results in homogenized responses that fail to address diverse user preferences. Existing training-free methods often occupy valuable context windows through prompt engineering,...

arXiv cs.AI

Reinforcement Learning with Decomposed Subtasks

Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire multi-turn rollout into a single scalar trajectory reward before it enters the policy update. When the task composes distinct skills, especially under sparse and delayed environmental...

arXiv cs.LG

QUARTET: Quad-branch cross-Attention and Random-walk Traces for Enhancing Transformers on Relational Graphs

Relational Deep Learning (RDL) models multi-table databases as heterogeneous temporal graphs, and graph transformers currently achieve state-of-the-art performance on benchmarks like RelBench. However, the current leading model, RelGT, suffers from two key limitations: its random local sampler yields loosely...

arXiv cs.AI

Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations

Wake word detection is a critical component of virtual assistants, serving as the gateway to seamless user interactions. This paper introduces a novel wake-up system that extends traditional direct keyword detection with contextual trigger detection. After an initial wake word activation, the system uses reasoning...

arXiv cs.LG

Marginally Correct Tool Caches Can Reverse Group-Normalized Policy Updates

Tool-result caching reduces repeated execution in agent training, but also couples rollout randomness. We study a two-action model in which independent and shared execution preserve every rollout's conditional reward distribution. Despite this marginal agreement, sharing one stochastic result per group can reverse...

arXiv cs.AI

Are Stated Reasoning Steps Causally Load-Bearing?

Chain-of-thought (CoT) monitoring assumes that the reasoning a model writes reflects the computation that directly produces its answer. Previous faithfulness metrics have been predominantly behavioral, as they simply edit the reasoning text and observe the resulting answer. However, our methodology aims to measure...

arXiv cs.LG

PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation

Many physical data assimilation (DA) workflows require smoothing methods that represent non-Gaussian posteriors over physical state variables, scale to high-dimensional simulators, train from observation windows alone, and remain compatible with calibration of the prescribed simulator. We introduce PR-Smoother, a...

Aktuelle Daily Papers

Von Hugging Face

Hugging Face Daily Papers

The Linear Representation Hypothesis Needs a Group Action

To make claims about representations that generalize beyond a particular trained model, we need to specify when two representations should count as equivalent. The Linear Representation Hypothesis is often discussed without making this equivalence explicit. Different notions of equivalence preserve different...

Hugging Face Daily Papers

Knowledge Pull Requests for Continual Document Authoring

We introduce Knowledge Pull Requests (KPRs), a framework for continual document authoring that makes each change interpretable. Documents require ongoing revision as new knowledge surfaces from other sources, languages, or times, but existing approaches either edit with no account of what knowledge changed or...

Hugging Face Daily Papers

Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to externalize intermediate...

Hugging Face Daily Papers

X-Planner: Event-Structured Task Planning for Embodied Intelligence

Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems often leave this intermediate structure implicit. Existing chain-of-thought (CoT) planners also tend to rely on coarse task-level annotations or serialize long...

Hugging Face Daily Papers

Calibration as a First-Class Criterion in LLM Evaluation

Calibration of language models -- the alignment between expressed or implicit confidence and empirical correctness -- is a well-studied subfield within NLP. Methods to measure it already exist. The problem is adoption: outside this subfield, NLP research regularly introduces new models, datasets, and benchmarks...

Hugging Face Daily Papers

FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation

Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distribution. However, this memoryless approach is inherently suboptimal: because it lacks awareness of prior generations and their evaluations, it...

Hugging Face Daily Papers

GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression

Transformer architectures exhibit cross-layer redundancies, yet post-training compression pipelines typically optimize layers in isolation or rely on heuristic grouping strategies that disregard layer-specific activation geometries. We introduce a principled, training-free framework that sequentially optimizes...

Hugging Face Daily Papers

Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery

Pruning large pre-trained transformer-based ASR models such as OpenAI's Whisper has seen great adoption, as pruning the decoder led to significant end-to-end transcription speedups. For instance, the tt whisper-large-v3-turbo variant reduced the decoder from 32 to 4 layers, while Distill-Whisper similarly reduced...

Hugging Face Daily Papers

Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI

Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned...

Hugging Face Daily Papers

MemoryAthena: Adaptive Routing over Latent and Generated Memories

Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be modified independently. We study whether useful memory can also be generated rather than only retrieved. MemoryAthena uses three pathways: direct Engram retrieval...

Hugging Face Daily Papers

On the Diffusibility of High-Dimensional Latents

Representation Autoencoders (RAEs) enable diffusion models to operate in the feature spaces of pretrained visual encoders. However, many off-the-shelf encoders are not optimized for faithful reconstruction, discarding fine-grained visual details. As expected, finetuning these encoders for image reconstruction...

Hugging Face Daily Papers

All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation

Video is a rich representation of a physical event, capturing appearance, geometry, motion, and temporal evolution. Other modalities, such as 3D body motion or audio, encode narrower aspects of the same event. We find that joint multimodal diffusion transformers exhibit a corresponding asymmetry in cross-modal...

Hugging Face Daily Papers

PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

Robotic bin packing requires long-horizon sequential decision-making, as each object placement affects the available space for subsequent packing. Existing methods primarily rely on hand-crafted geometric heuristics that optimize predefined objectives or reinforcement learning policies learned through trial and...

Hugging Face Daily Papers

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local state transitions caused by object motion and viewpoint changes and integrate them over long trajectories to maintain an updated spatial...

Hugging Face Daily Papers

HappyWorld-Bench

Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, interaction, and modification. We introduce HappyWorld-Bench, a comprehensive benchmark that evaluates whether generated worlds remain reliable as agents interact with...

Hugging Face Daily Papers

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is completed, its trajectory is distilled into a fixed artifact, such as a reflection, workflow, skill, or reasoning strategy, that is later retrieved by similarity. This...

Hugging Face Daily Papers

EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics

We study coding agents for long-horizon, dexterous robotics and ask whether their solutions can provide scalable supervision for learning general robot policies. To test this, we develop EMBODIEDSWE-BENCH, a simulation benchmark for coding agents spanning contact-rich manipulation, deformable objects, and...

Hugging Face Daily Papers

StudentBench: AI and human tutoring yield equivalent GRE learning gains

Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We introduce StudentBench, a suite of AI teaching evaluations and a public platform that enables large-scale data collection with over...

Hugging Face Daily Papers

MemBodied: Recurrent Associative Memory for Vision-Language-Action Models

Vision-Language-Action models provide a strong foundation for general-purpose robot control, yet a vast majority of policies do not preserve and leverage episode-level information beyond the current observation. This limitation is consequential in history-dependent manipulation tasks that depend on information...

Hugging Face Daily Papers

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information is shared by the group, and how states change over time. Recent...