arXiv:2603.05541v1 Announce Type: new Abstract: Collaborative training across multiple institutions is becoming essential for building reliable medical image segmentation models. However, privacy regulations, data silos, and uneven data availability prevent hospitals from sharing raw scans or annotations, limiting the ability to train generalizable models. Latent-space collaboration frameworks such as privacy-segmentation framework (SF) offer a promising […]
Predictive Coding Graphs are a Superset of Feedforward Neural Networks
arXiv:2603.06142v1 Announce Type: cross Abstract: Predictive coding graphs (PCGs) are a recently introduced generalization to predictive coding networks, a neuroscience-inspired probabilistic latent variable model. Here, we prove how PCGs define a mathematical superset of feedforward artificial neural networks (multilayer perceptrons). This positions PCNs more strongly within contemporary machine learning (ML), and reinforces earlier proposals to […]
The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$rightarrow$LLM Pipelines?
arXiv:2602.17598v2 Announce Type: replace-cross Abstract: Speech LLMs are widely understood to be better than ASR$rightarrow$LLM cascades since they have access to the audio directly, and not just the transcript. In this paper, we present an evaluation methodology and a mechanistic interpretation of the observed behavior of speech LLMs. First, we introduce matched-backbone testing which separates […]
MAPO: Mixed Advantage Policy Optimization for Long-Horizon Multi-Turn Dialogue
arXiv:2603.06194v1 Announce Type: cross Abstract: Subjective multi-turn dialogue tasks, such as emotional support, require conversational policies that adapt to evolving user states and optimize long-horizon interaction quality. However, reinforcement learning (RL) for such settings remains challenging due to the absence of reliable process supervision. Outcome-only training collapses credit assignment across turns into a single trajectory-level […]
The World Won’t Stay Still: Programmable Evolution for Agent Benchmarks
arXiv:2603.05910v1 Announce Type: new Abstract: LLM-powered agents fulfill user requests by interacting with environments, querying data, and invoking tools in a multi-turn process. Yet, most existing benchmarks assume static environments with fixed schemas and toolsets, neglecting the evolutionary nature of the real world and agents’ robustness to environmental changes. In this paper, we study a […]
Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering
arXiv:2603.06271v1 Announce Type: cross Abstract: Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. These systems iteratively retrieve curated domain knowledge and synthesize it into structured reports before answer selection. Although such pipelines can improve performance, their impact on reliability under model variability […]
Measuring AI R&D Automation
arXiv:2603.03992v3 Announce Type: replace-cross Abstract: The automation of AI R&D (AIRDA) could have significant implications, but its extent and ultimate effects remain uncertain. We need empirical data to resolve these uncertainties, but existing data (primarily capability benchmarks) may not reflect real-world automation or capture its broader consequences, such as whether AIRDA accelerates capabilities more than […]
K-MaT: Knowledge-Anchored Manifold Transport for Cross-Modal Prompt Learning in Medical Imaging
arXiv:2603.06340v1 Announce Type: cross Abstract: Large-scale biomedical vision-language models (VLMs) adapted on high-end imaging (e.g., CT) often fail to transfer to frontline low-end modalities (e.g., radiography), collapsing into modality-specific shortcuts. We propose K-MaT (Knowledge-Anchored Manifold Transport), a prompt-learning framework that transfers decision structures to low-end modalities without requiring low-end training images. K-MaT factorizes prompts, anchors […]
DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality
arXiv:2603.05912v1 Announce Type: new Abstract: Search-augmented LLM agents can produce deep research reports (DRRs), but verifying claim-level factuality remains challenging. Existing fact-checkers are primarily designed for general-domain, factoid-style atomic claims, and there is no benchmark to test whether such verifiers transfer to DRRs. Yet building such a benchmark is itself difficult. We first show that […]
LiveSense: A Real-Time Wi-Fi Sensing Platform for Range-Doppler on COTS Laptop
arXiv:2603.06545v1 Announce Type: cross Abstract: We present LiveSense – a cross-platform that transforms a commercial off-the-shelf (COTS) Wi-Fi Network Interface Card (NIC) on a laptop into a centimeter-level Range-Doppler sensor while preserving simultaneous communication capability. The laptops are equipped with COTS Intel AX211 (Wi-Fi 6E) or Intel BE201 (Wi-Fi 7) NICs. LiveSense can (i) Extract […]
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
arXiv:2603.05890v1 Announce Type: cross Abstract: What happens when a storyteller forgets its own story? Large Language Models (LLMs) can now generate narratives spanning tens of thousands of words, but they often fail to maintain consistency throughout. When generating long-form narratives, these models can contradict their own established facts, character traits, and world rules. Existing story […]
An Interactive Multi-Agent System for Evaluation of New Product Concepts
arXiv:2603.05980v1 Announce Type: new Abstract: Product concept evaluation is a critical stage that determines strategic resource allocation and project success in enterprises. However, traditional expert-led approaches face limitations such as subjective bias and high time and cost requirements. To support this process, this study proposes an automated approach utilizing a large language model (LLM)-based multi-agent […]