arXiv:2601.15322v1 Announce Type: new Abstract: LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, most deployments fail to return consistent results. This paper introduces the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism and evidence-conditioned faithfulness in tool-using agents deployed in financial services. Across 74 configurations (12 models, 4 providers, 8-24 runs each at T=0.0) in non-agentic baseline experiments, 7-20B parameter models achieved 100% determinism, while 120B+ […]

Ver mais

arXiv:2603.05551v1 Announce Type: new Abstract: Information-intensive Document Question Answering (DocQA) is often constrained by long contexts and information overload, which hinders Vision-Language Models (VLMs) from performing precise direct reasoning. Although multimodal GraphRAG has achieved preliminary breakthroughs, existing frameworks still face dual challenges: (1) the necessity of large-scale models for handling queries of diverse complexities and (2) the inherent reasoning bottlenecks of end-to-end VLMs. To address these issues, we propose AutoThinkRAG, a framework that enhances the understanding of complex […]

Ver mais

This paper addresses the limitations of traditional protocol anomaly detection methods in handling dynamic state changes and unstructured behaviors. A deep protocol anomaly detection algorithm based on status code sequence modeling is proposed. The method uses the status codes returned during protocol communication as the core input. A state embedding layer is employed to transform discrete status codes into continuous vector representations. A gated recurrent unit (GRU) is then used to capture temporal dependencies and behavior patterns within […]

Ver mais

arXiv:2603.10035v1 Announce Type: new Abstract: Research in emergency triage is restricted to structured electronic health records (EHR) due to regulatory constraints on nurse-patient interactions. We introduce TriageSim, a simulation framework for generating persona-conditioned triage conversations from structured records. TriageSim enables multi-turn nurse-patient interactions with explicit control over disfluency and decision behaviour, producing a corpus of ~800 synthetic transcripts and corresponding audio. We use a combination of automated analysis for linguistic, behavioural and acoustic fidelity alongside manual evaluation for […]

Ver mais

Post Content

Ver mais

Hey Hackers! Welcome to the second-ever edition of HackerNoon Projects of the Week, where we spotlight standout projects from the Proof of Usefulness Hackathon, HackerNoon’s competition designed to measure what actually matters: real utility over hype. This week, we’re excited to share three amazing projects that have proven their necessity and usefulness: Agent Observatory, Formonger, and Olio AI. Introducing the Projects of the Week! Agent Observatory https://hackernoon.com/agent-observatory-earns-a-56-proof-of-usefulness-score-by-making-ai-agents-observable-without-risk?embedable=true If you’re a backend or platform engineer, then Agent Observatory is the […]

Ver mais

Accurate and efficient 3D medical image segmentation is essential for clinical AI, where models must remain reliable under stringent memory, latency, and data availability constraints. Transformer-based methods achieve strong accuracy but suffer from excessive parameters, high FLOPs, and limited generalization. We propose LightMedSeg, a modular UNet-style segmentation architecture that integrates anatomical priors with adaptive context modeling. Anchor-conditioned FiLM modulation enables anatomy-aware feature calibration, while a local structural prior module and texture-aware routing dynamically allocate representational capacity to boundary-rich […]

Ver mais