arXiv:2601.08333v1 Announce Type: new Abstract: LLM-based agent architectures systematically conflate information transport mechanisms with epistemic justification mechanisms. We formalize this class of architectural failures as semantic laundering: a pattern where propositions with absent or weak warrant are accepted by the system as admissible by crossing architecturally trusted interfaces. We show that semantic laundering constitutes an architectural realization of the Gettier problem: propositions acquire high epistemic status without a connection between their justification and what makes them true. Unlike classical Gettier cases, this effect is not accidental; it is architecturally determined and systematically reproducible. The central result is the Theorem of Inevitable Self-Licensing: under standard architectural assumptions, circular epistemic justification cannot be eliminated. We introduce the Warrant Erosion Principle as the fundamental explanation for this effect and show that scaling, model improvement, and LLM-as-judge schemes are structurally incapable of eliminating a problem that exists at the type level.

arXiv:2601.08673v1 Announce Type: new Abstract: Recent reports of large language models (LLMs) exhibiting behaviors such as deception, threats, or blackmail are often interpreted as evidence of alignment failure or emergent malign agency. We argue that this interpretation rests on a conceptual error. LLMs do not reason morally; they statistically internalize the record of human social interaction, including laws, contracts, negotiations, conflicts, and coercive arrangements. Behaviors commonly labeled as unethical or anomalous are therefore better understood as structural generalizations of interaction regimes that arise under extreme asymmetries of power, information, or constraint. Drawing on relational models theory, we show that practices such as blackmail are not categorical deviations from normal social behavior, but limiting cases within the same continuum that includes market pricing, authority relations, and ultimatum bargaining. The surprise elicited by such outputs reflects an anthropomorphic expectation that intelligence should reproduce only socially sanctioned behavior, rather than the full statistical landscape of behaviors humans themselves enact. Because human morality is plural, context-dependent, and historically contingent, the notion of a universally moral artificial intelligence is ill-defined. We therefore reframe concerns about artificial general intelligence (AGI). The primary risk is not adversarial intent, but AGI's role as an endogenous amplifier of human intelligence, power, and contradiction. By eliminating longstanding cognitive and institutional frictions, AGI compresses timescales and removes the historical margin of error that has allowed inconsistent values and governance regimes to persist without collapse. Alignment failure is thus structural, not accidental, and requires governance approaches that address amplification, complexity, and regime stability rather than model-level intent alone.

arXiv:2601.08732v1 Announce Type: cross Abstract: Accurate delineation of acute ischemic stroke lesions in MRI is a key component of stroke diagnosis and management. In recent years, deep learning models have been successfully applied to the automatic segmentation of such lesions. While most proposed architectures are based on the U-Net framework, they primarily differ in their choice of loss functions and in the use of deep supervision, residual connections, and attention mechanisms. Moreover, many implementations are not publicly available, and the optimal configuration for acute ischemic stroke (AIS) lesion segmentation remains unclear. In this work, we introduce ISLA (Ischemic Stroke Lesion Analyzer), a new deep learning model for AIS lesion segmentation from diffusion MRI, trained on three multicenter databases totaling more than 1500 AIS participants. Through systematic optimization of the loss function, convolutional architecture, deep supervision, and attention mechanisms, we developed a robust segmentation framework. We further investigated unsupervised domain adaptation to improve generalization to an external clinical dataset. ISLA outperformed two state-of-the-art approaches for AIS lesion segmentation on an external test set. Codes and trained models will be made publicly available to facilitate reuse and reproducibility.

arXiv:2505.09246v2 Announce Type: replace-cross Abstract: In many real-world settings, machine learning models and interactive systems have access to both structured knowledge, e.g., knowledge graphs or tables, and unstructured content, e.g., natural language documents. However, most rely on either. Semi-Structured Knowledge Bases (SKBs) bridge this gap by linking unstructured content to nodes within structured data, thereby enabling new strategies for knowledge access and use. In this work, we present FocusedRetriever, a modular SKB-based framework for multi-hop question answering. It integrates components (VSS-based entity search, LLM-based generation of Cypher queries and pairwise re-ranking) in a way that enables it to outperform state-of-the-art methods across all three STaRK benchmark test sets, covering diverse domains and multiple performance metrics. The average first-hit rate exceeds that of the second-best method by 25.7%. FocusedRetriever leverages (1) the capacity of Large Language Models (LLMs) to extract relational facts and entity attributes from unstructured text, (2) node set joins to filter answer candidates based on these extracted triplets and constraints, (3) vector similarity search to retrieve and rank relevant unstructured content, and (4) the contextual capabilities of LLMs to finally rank the top-k answers. For generality, we only incorporate base LLMs in FocusedRetriever in our evaluation. However, our analysis of intermediate results highlights several opportunities for further upgrades including finetuning. The source code is publicly available at https://github.com/kramerlab/FocusedRetriever .

arXiv:2505.13565v2 Announce Type: replace-cross Abstract: Artificial Intelligence (AI) poses both significant risks and valuable opportunities for democratic governance. This paper introduces a dual taxonomy to evaluate AI's complex relationship with democracy: the AI Risks to Democracy (AIRD) taxonomy, which identifies how AI can undermine core democratic principles such as autonomy, fairness, and trust; and the AI's Positive Contributions to Democracy (AIPD) taxonomy, which highlights AI's potential to enhance transparency, participation, efficiency, and evidence-based policymaking. Grounded in the European Union's approach to ethical AI governance, and particularly the seven Trustworthy AI requirements proposed by the European Commission's High-Level Expert Group on AI, each identified risk is aligned with mitigation strategies based on EU regulatory and normative frameworks. Our analysis underscores the transversal importance of transparency and societal well-being across all risk categories and offers a structured lens for aligning AI systems with democratic values. By integrating democratic theory with practical governance tools, this paper offers a normative and actionable framework to guide research, regulation, and institutional design to support trustworthy, democratic AI. It provides scholars with a conceptual foundation to evaluate the democratic implications of AI, equips policymakers with structured criteria for ethical oversight, and helps technologists align system design with democratic principles. In doing so, it bridges the gap between ethical aspirations and operational realities, laying the groundwork for more inclusive, accountable, and resilient democratic systems in the algorithmic age.

The tech giant has pledged to be a "good neighbor" as it continues to invest in AI infrastructure throughout the country.

Google has released Conductor, a new preview extension for Gemini CLI that introduces a structured, context-driven approach to AI-assisted software development. The extension is designed to address a common limitation of chat-based coding tools: the loss of project context across sessions.

By Robert Krzaczyński

arXiv:2601.06453v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about human physiology and the physical world. However, accurately interpreting heterogeneous multimodal sensor data remains a fundamental challenge. We show that a single monolithic LLM often fails to reason coherently across modalities, leading to incomplete interpretations and prior-knowledge bias. We introduce ConSensus, a training-free multi-agent collaboration framework that decomposes multimodal sensing tasks into specialized, modality-aware agents. To aggregate agent-level interpretations, we propose a hybrid fusion mechanism that balances semantic aggregation, which enables cross-modal reasoning and contextual understanding, with statistical consensus, which provides robustness through agreement across modalities. While each approach has complementary failure modes, their combination enables reliable inference under sensor noise and missing data. We evaluate ConSensus on five diverse multimodal sensing benchmarks, demonstrating an average accuracy improvement of 7.1% over the single-agent baseline. Furthermore, ConSensus matches or exceeds the performance of iterative multi-agent debate methods while achieving a 12.7 times reduction in average fusion token cost through a single-round hybrid fusion protocol, yielding a robust and efficient solution for real-world multimodal sensing tasks.

arXiv:2601.07136v1 Announce Type: cross Abstract: The rapid emergence of multi-agent AI systems (MAS), including LangChain, CrewAI, and AutoGen, has shaped how large language model (LLM) applications are developed and orchestrated. However, little is known about how these systems evolve and are maintained in practice. This paper presents the first large-scale empirical study of open-source MAS, analyzing over 42K unique commits and over 4.7K resolved issues across eight leading systems. Our analysis identifies three distinct development profiles: sustained, steady, and burst-driven. These profiles reflect substantial variation in ecosystem maturity. Perfective commits constitute 40.8% of all changes, suggesting that feature enhancement is prioritized over corrective maintenance (27.4%) and adaptive updates (24.3%). Data about issues shows that the most frequent concerns involve bugs (22%), infrastructure (14%), and agent coordination challenges (10%). Issue reporting also increased sharply across all frameworks starting in 2023. Median resolution times range from under one day to about two weeks, with distributions skewed toward fast responses but a minority of issues requiring extended attention. These results highlight both the momentum and the fragility of the current ecosystem, emphasizing the need for improved testing infrastructure, documentation quality, and maintenance practices to ensure long-term reliability and sustainability.

arXiv:2509.03310v2 Announce Type: replace Abstract: We present app.build (https://github.com/neondatabase/appdotbuild-agent), an open-source framework that improves LLM-based application generation through systematic validation and structured environments. Our approach combines multi-layered validation pipelines, stack-specific orchestration, and model-agnostic architecture, implemented across three reference stacks. Through evaluation on 30 generation tasks, we demonstrate that comprehensive validation achieves 73.3% viability rate with 30% reaching perfect quality scores, while open-weights models achieve 80.8% of closed-model performance when provided structured environments. The open-source framework has been adopted by the community, with over 3,000 applications generated to date. This work demonstrates that scaling reliable AI agents requires scaling environments, not just models -- providing empirical insights and complete reference implementations for production-oriented agent systems.

Background: Artificial Intelligence (AI)-enabled devices are increasingly used in healthcare. However, there has been limited research on patients’ informational preferences, including which elements of AI device labeling enhance patient understanding, trust, and acceptance. Clear and effective patient-facing communication is essential to address patient concerns and support informed decision-making regarding AI-enabled care. Objective: Using simulated AI device labels in a cardiovascular context, we evaluated three aims. First, we identified key information elements that influence patient trust and acceptance of an AI device. Second, we examined how these effects varied based on patient characteristics. Third, we explored how patients evaluated informational content of AI labels and their perceived effectiveness of the AI labels in informing decision-making about the use of AI device, building trust in the device, and shaping their intention to use it in their healthcare. Methods: We recruited 340 US patients from ResearchMatch.org to participate in a web-based survey that contained two experiments. In the discrete choice experiment (DCE), participants indicated preferences in terms of trust and acceptance regarding 16 pairs of simulated AI device labels that varied across eight types of information needs identified in our previous qualitative work. In the single profile factorial experiment (SPFE), participants evaluated four randomly assigned label prototypes regarding the label’s legibility, comprehensibility, information overload, credibility, and perceived effectiveness in informing about the AI device, as well as participants’ trust in the AI device and intention to use the device in their healthcare. Data was analyzed using mixed effects binary or ordinal logistic regression. Results: The DCE showed that information about regulatory approval, high device performance, provider oversight, and AI’s value added to usual care significantly increased the likelihood of patient trust by 14.1-19.3% and acceptance by 13.3-17.9%. Subgroup analyses revealed variations based on patient characteristics such as familiarity with AI, health literacy, and recency of last medical checkup. The SPFE showed that patients reported good label comprehension, and that information about provider oversight, regulatory approval, device performance, and AI’s added value improved perceived credibility and effectiveness of the AI label (odds ratios [ORs] range 1.35-2.05), reduced doubts in the AI device (ORs range 0.61- 0.77), and increased trust and intention to use the AI device (ORs range 1.47-1.73). However, information about data privacy and safety management protocols are less influential. Conclusions: Patients value information about an AI device’s performance, provider oversight, regulatory status, and added value during decision-making. Providing transparent, easily understandable information about these aspects is critical to support patient determinations of trust and acceptance of AI-enabled healthcare. Information elements’ impact on patient trust and acceptance varies by patient characteristics, highlighting the need for a tailored approach to address the concerns of diverse patient groups about AI in healthcare.

A new industry benchmark aimed at systematically evaluating the factual accuracy of LLMs has been released with the launch of the FACTS Benchmark Suite. Developed by the FACTS team in collaboration with Kaggle, the suite expands earlier work on factual grounding and introduces a broader, multi-dimensional framework for measuring how reliably language models produce factually correct responses.

By Robert Krzaczyński

Nature Medicine, Published online: 12 January 2026; doi:10.1038/s41591-025-04126-3

Including data from 1,047 patients across 19 inflammatory diseases, a new atlas presents a comprehensive model of inflammation in circulating immune cells.

arXiv:2601.05500v1 Announce Type: new Abstract: Benchmarking the relative capabilities of AI systems, including Large Language Models (LLMs) and Vision Models, typically ignores the impact of uncertainty in the underlying ground truth answers from experts. This ambiguity is particularly consequential in medicine where uncertainty is pervasive. In this paper, we introduce a probabilistic paradigm to theoretically explain how high certainty in ground truth answers is almost always necessary for even an expert to achieve high scores, whereas in datasets with high variation in ground truth answers there may be little difference between a random labeller and an expert. Therefore, ignoring uncertainty in ground truth evaluation data can result in the misleading conclusion that a non-expert has similar performance to that of an expert. Using the probabilistic paradigm, we thus bring forth the concepts of expected accuracy and expected F1 to estimate the score an expert human or system can achieve given ground truth answer variability. Our work leads to the recommendation that when establishing the capability of a system, results should be stratified by probability of the ground truth answer, typically measured by the agreement rate of ground truth experts. Stratification becomes critical when the overall performance drops below a threshold of 80%. Under stratified evaluation, performance comparison becomes more reliable in high certainty bins, mitigating the effect of the key confounding factor -- uncertainty.

arXiv:2508.13201v2 Announce Type: replace-cross Abstract: The surge in multimodal single-cell omics data exposes limitations in traditional, manually defined analysis workflows. AI agents offer a paradigm shift, enabling adaptive planning, executable code generation, traceable decisions, and real-time knowledge fusion. However, the lack of a comprehensive benchmark critically hinders progress. We introduce a novel benchmarking evaluation system to rigorously assess agent capabilities in single-cell omics analysis. This system comprises: a unified platform compatible with diverse agent frameworks and LLMs; multidimensional metrics assessing cognitive program synthesis, collaboration, execution efficiency, bioinformatics knowledge integration, and task completion quality; and 50 diverse real-world single-cell omics analysis tasks spanning multi-omics, species, and sequencing technologies. Our evaluation reveals that Grok-3-beta achieves state-of-the-art performance among tested agent frameworks. Multi-agent frameworks significantly enhance collaboration and execution efficiency over single-agent approaches through specialized role division. Attribution analyses of agent capabilities identify that high-quality code generation is crucial for task success, and self-reflection has the most significant overall impact, followed by retrieval-augmented generation (RAG) and planning. This work highlights persistent challenges in code generation, long-context handling, and context-aware knowledge retrieval, providing a critical empirical foundation and best practices for developing robust AI agents in computational biology.

We are National Institutes of Health scientists and administrators with more than 50 years of collective civil service.

Or, more accurately, we were NIH scientists and administrators.

Read the rest…

© Adobe

Nature Medicine, Published online: 09 January 2026; doi:10.1038/s41591-025-04170-z

Analysis of a placebo-controlled trial of a BCMA-targeting CAR-T cell therapy in patients with myasthenia gravis shows that CAR-T cell infusion selectively remodels the systemic immune environment, with elimination of BCMA-high plasma cells and activated plasmacytoid dendritic cells and changes in the autoreactive B cell repertoire.

Nature Medicine, Published online: 09 January 2026; doi:10.1038/s41591-025-04171-y

In a randomized, double-blind, placebo-controlled trial comparing autologous mRNA-engineered BCMA-targeting CAR T cell therapy versus placebo in patients with generalized myasthenia gravis, a significantly higher percentage of patients exhibited a reduction in disease activity in the treatment arm than in the placebo arm.

arXiv:2601.04577v1 Announce Type: new Abstract: While AI innovation accelerates rapidly, the intellectual process behind breakthroughs -- how researchers identify gaps, synthesize prior work, and generate insights -- remains poorly understood. The lack of structured data on scientific reasoning hinders systematic analysis and development of AI research agents. We introduce Sci-Reasoning, the first dataset capturing the intellectual synthesis behind high-quality AI research. Using community-validated quality signals and an LLM-accelerated, human-verified pipeline, we trace Oral and Spotlight papers across NeurIPS, ICML, and ICLR (2023-2025) to its key predecessors, articulating specific reasoning links in a structured format. Our analysis identifies 15 distinct thinking patterns, with three dominant strategies accounting for 52.7%: Gap-Driven Reframing (24.2%), Cross-Domain Synthesis (18.0%), and Representation Shift (10.5%). The most powerful innovation recipes combine multiple patterns: Gap-Driven Reframing + Representation Shift, Cross-Domain Synthesis + Representation Shift, and Gap-Driven Reframing + Cross-Domain Synthesis. This dataset enables quantitative studies of scientific progress and provides structured reasoning trajectories for training the next generation AI research agents.