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-guex5c23zfm5Okt. 2026

Multi-Agenten-KI als verschachteltes Prinzipal-Agent-Problem in der privaten Vermögensverwaltung

Mandatsrepräsentation und Nachweiskontrolle in der Schweiz, Deutschland und Österreich

DOI 10.5281/zenodo.23095194

arXiv 2610.02863

Walter Kurz¹, Reinhard Magg¹, Florian Kollberg², Wojtek Stricker¹, Stefan Marx², Frank Reinhardt², Velimir Dedić³

¹Swissi Institute for AI²Hochschule für Wirtschaft und Umwelt Nürtingen-Geislingen³Faculty of Information Technology and Engineering (FITI), Belgrade

Eine verschachtelte Formulierung der Beziehung zwischen Kundschaft, Vermögensverwaltung und KI erfasst die Ergebnisse beider Parteien getrennt und definiert eine gemeinsame Zielfunktion unter Nebenbedingungen. Analytische Konstruktionen und Simulationen untersuchen, wie Mandatsrepräsentation, Klärung und nachweisgebundene Freigabe Empfehlungen beeinflussen.

Schlagwörter:

Multi-Agenten-KI
private Vermögensverwaltung
verschachteltes Prinzipal-Agent-Problem
Mandatsrepräsentation
gemeinsame Zielfunktion
Spezifikationsrisiko
Eignung
Herkunft von Prämissen
menschliche Aufsicht

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

arXiv 2610.00287

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

arXiv 2609.29108

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

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this...

arXiv cs.LG

User Embeddings are Superpositions of Interpretable Behavioral Modes

User embeddings are central components of modern recommendation, personalization, and behavioral modeling systems. Though these embeddings can compactly encode rich behavioral information, they are inherently dense and opaque, limiting interpretability. To address this gap, we argue that user embeddings can be...

arXiv cs.AI

Scientist World: Grow a Research World for AI-Scientists

AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted - centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every research paper becomes...

arXiv cs.LG

XStack: A Benchmark for ML Repo Migration

ML code should run where researchers choose, not where it was first written. Today, machine learning code mainly lives in two ecosystems, PyTorch on NVIDIA GPUs and JAX on Google TPUs. Migrating repositories between them means building and testing across frameworks and hardware. This migration is (1) a practical...

arXiv cs.AI

Same Behavior, Different Mechanism: What Finite Experiments Can Certify About Integrated Information

Interpretability, AI auditing and assessments of machine consciousness increasingly rest on mechanism-level quantities: functionals of a system's causal transition law that describe how it computes, not what it outputs. Experiments see that law only through finite, partial and noisy interventions. We ask when such...

arXiv cs.LG

Towards interpreting any residual stream direction by scaling activation inversion

To interpret a direction in a language model's residual stream, we can look for text that strongly activates it. But when such text is found by scanning a corpus, it is limited to what that corpus contains. We develop Maximally-Activating Example Metamodels (MAEMs), language models which map residual stream...

arXiv cs.AI

ReproBridge: Building Reproducibility into ML Research Artifacts

Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to fill in missing details, rather than on the released artifacts alone. We ask...

arXiv cs.LG

Adversarial Training with Large Step Sizes: Implicit Bias, Optimization, and Sharpness

Adversarial Training (AT) is an important method for improving model robustness. We study the dynamics of deterministic Gradient Descent (GD) in AT. Most existing works in this direction focus on the small or vanishing step sizes regime, where GD resembles a continuous-time flow. However, such step sizes can make...

arXiv cs.AI

Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes

Typed-decision models score options that the caller supplies at request time, so their accuracy depends on label wording that the model's developer does not control. We compare two releases of a 307M-parameter multilingual cross-encoder, Ru-Jev, trained on thirteen Russian-language tasks; the later release adds an...

arXiv cs.LG

Unpacking the Compute Efficiency of Strong-to-Weak OPD against GRPO

On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher's per-token supervision. Does this dense signal reduce the training FLOPs needed to reach a target accuracy compared with reinforcement learning? We systematically compare vanilla reverse-KL OPD with Group Relative Policy...

arXiv cs.AI

Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety

Neural networks are likely to be among the most consequential artefacts in human history. As these systems become more capable and autonomous, their potential to cause societal harm also grows, making AI safety one of the defining challenges of our time. Yet we continue to build increasingly powerful systems...

arXiv cs.LG

A Hidden Markov Preference Model for Online Prediction of Adversary Actions

A defender anticipating an attacker needs a probability distribution over the attacker's next action from information available before that action occurs. Two structures complicate this: the attacker's behavioral regime persists and can switch within an episode, and each action combines an operation with...

arXiv cs.AI

MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue

LLM-based medical assistants that follow a patient across visits need a memory that keeps the patient's clinical state correct as it changes. We examine the errors of five memory systems on longitudinal medical dialogue and find three recurring causes: the retrieved evidence gives an outdated state, includes...

arXiv cs.LG

Data-driven discovery of intrinsic Lie point symmetries of differential equation systems

Discovering continuous symmetries directly from differential-equation data can reveal geometric structure for model reduction and scientific machine learning without symbolic determining equations or a closed-form representation of the governing system. We formulate intrinsic Lie point-symmetry discovery as an...

arXiv cs.AI

The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI

Chat remains the default surface for many large language model (LLM) tasks, even as agentic tools such as OpenCode excel at coding and automation. Yet the model sees the current dialogue but not the workspace around it. We explore meta access---giving the assistant a structured, permissioned view of the interface...

arXiv cs.LG

On the limitations of molecular representations

Molecular representations such as fingerprints and learned embeddings play a central role in cheminformatics and small-molecule machine learning. They serve as the primary input for a diverse array of tasks, including clustering, dataset splitting, and virtual screening, yet their evaluation is often limited to...

arXiv cs.AI

Failure Prediction and Classification in Vision-Language-Action Models Via Calibrated Latent Probing

Vision-Language-Action models (VLAs) enable general-purpose embodied intelligence, but their performance is brittle under distribution shift, where unanticipated failures can damage equipment or endanger people. Deploying VLAs in real-world systems therefore requires a runtime monitor that is timely, calibrated,...

arXiv cs.LG

Spectral and Subspace Dynamics of LoRA in Supervised Fine-Tuning and Reinforcement Learning

Low-rank adaptation (LoRA) is commonly used in both supervised fine-tuning (SFT) and reinforcement learning (RL), often under similar optimizer settings. Yet, how the different dynamics of the two stages manifest in the low-rank increment that LoRA optimizes remains unclear. Tracking the singular spectrum and...

arXiv cs.AI

Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks

Coding agents are among the most economically consequential deployments of LLMs to date, making reliable evaluation increasingly important. Yet even benchmarks that are carefully validated at release can become stale. As models improve, they can discover valid solutions that existing verifiers reject, while changes...

arXiv cs.LG

Conformal Prediction for Time-Dependent PDEs

Uncertainty quantification is crucial in scientific machine learning, where models inform safety-critical tasks such as flood forecasting, financial risk management, and thermal control in machines. Conformal prediction provides distribution-free coverage guarantees, but in time-dependent settings common to physics...

Aktuelle Daily Papers

Von Hugging Face

Hugging Face Daily Papers

Tools Need Not Speak in Text: Latent Context Compression for Agents

Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long and noisy observations incur substantial context overhead and dilute the agent's attention to task-relevant information. Existing token pruning and summarization methods remain constrained by...

Hugging Face Daily Papers

Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation

Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors. A signature proves who published a pack, not that its vectors encode its text. We study this text-vector integrity gap. A verifier that recomputes vectors and...

Hugging Face Daily Papers

StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models

A deployable text-to-image diffusion model must hold several capabilities at once, such as instruction following, text rendering and human preference, and must sample in a few steps. Capabilities and few-step sampling are built in separate stages: a full-step model first consolidates capabilities through...

Hugging Face Daily Papers

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

Hugging Face Daily Papers

OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery

Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level problems remains challenging. We introduce OpenFrontiers, a cross-disciplinary resource that combines a structured...

Hugging Face Daily Papers

Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling

Mathematical modeling turns an open-ended real-world problem into assumptions, a model, a solution, and a defended recommendation, and its answers matter only if they are both close to a credible reference and physically feasible; existing benchmarks either score solver fragments or grade reports with an LLM judge,...

Hugging Face Daily Papers

Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout

Linear attention compresses context into a fixed-size key-value state for linear-time training and constant-memory inference. Gated delta-rule models decay this state and erase its prediction for an incoming key before writing a new value; Gated DeltaNet-2 (GDN-2) generalizes this with channel-wise decay and...

Hugging Face Daily Papers

Information Games: Strategic Crowding and Firm Repositioning in Language-Model Space

When firms respond to new market opportunities, their capacity choices alter the future discounted free cash flows available to both competitors and investors. In competitive markets, these investment decisions publicized in news articles and analyst reports, measuring the changes in capital structure, product mix,...

Hugging Face Daily Papers

Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens

Embedding models compress variable-length text into fixed-size vector representations, but this compression can entangle semantic content with residual token-level information, such as artifacts arising from attention sink behavior. We propose a simple method that prepends trainable [DUMP] tokens to the input...

Hugging Face Daily Papers

Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition

Multi-head attention in Vision Transformers (ViTs) allows independent attention patterns across heads, but without explicit regularization, heads may learn redundant patterns rather than complementary roles. Correlation-based penalties encourage head disentanglement, yet apply uniform regularization across all...

Hugging Face Daily Papers

On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer

Prefill-to-Autoregressive Cross-model Transfer (PACT), a form of latent communication between language models, combines a larger model's prompt representations with a smaller model's efficient generation, offering a promising way to balance capability and inference cost. However, existing systems provide limited...

Hugging Face Daily Papers

Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation

LiDAR is a critical sensor for autonomous driving and robotics, yet it remains vulnerable to adverse conditions such as fog, rain, transparent objects, and low-reflectance surfaces. Full-waveform LiDAR (FWL) addresses these limitations by capturing the complete return waveform as a histogram, preserving rich...

Hugging Face Daily Papers

SynthFaces: Balanced Large Scale Human Dataset

The pursuit of fair and equitable AI in human-centric tasks is critically hindered by the inherent biases and privacy risks of real-world datasets, which offer imbalanced representations of identity and often contain sensitive personal information. Consequently, state-of-the-art generative models trained on this...

Hugging Face Daily Papers

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision Making (DPDM), an architecture that formulates heterogeneous agent decisions as conditional prediction with a shared pretrained learner....

Hugging Face Daily Papers

SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization

Mixture-of-Experts (MoE) models route each token to a few of many experts, yet what an individual expert is responsible for remains unsettled. Existing analyses count how often an expert is selected on domain-labeled corpora, an instrument that fixes the taxonomy in advance, stays coarse, and records selection...

Hugging Face Daily Papers

HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation

Recent advances in Vision-Language-Action (VLA) models have enabled fine manipulation capabilities, yet performing tasks that require working memory remains a key challenge. Most existing VLA architectures operate under a Markovian assumption, mapping only the current observation to an action, which leads to...

Hugging Face Daily Papers

TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing

Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. This long-term drift is often mitigated through training on multi-turn data or cross-turn rollouts, potentially...

Hugging Face Daily Papers

From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence

For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own. Large foundation models now write code and run multistep tasks, and personal agents act on a person's behalf. Yet people still forget what they once knew, miss what they are not looking at, fail to find the...

Hugging Face Daily Papers

EvoMemState: Evolving Memory State for Personal Agents

Long-term memory enables large language model (LLM) agents to provide continuous personalized assistance by retaining user information across interactions. Existing systems support this process through fact extraction, organization, updating, and retrieval, but largely maintain memories as independent facts. This...

Hugging Face Daily Papers

Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models

Chunk-interleaved full-duplex speech language models listen and speak in fixed time chunks, and each chunk must be processed before the next one arrives. Their workload is asymmetric across chunks: listen chunks leave compute idle while awaiting audio, and speak and tool-call chunks require serial generation, which...