Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (quant-ph) 2026-06-19

Quantum models with the Yang-Lee phase transition

arXiv:2606.19732v1 Announce Type: cross Abstract: In this article, we present four different $1+1$D quantum models that realize the Yang-Lee (YL) phase transition under a deformation that preserves $PT$ symmetry. These are the antiferromagnetic Ising spin chain in transverse and longitudinal magnetic fields, the massive Schwinger model, the Blume-Capel model, and the three-state quantum clock model. Using the state-operator correspondence, we identify the YL critical point, compute the scaling dimensions of the lowest operators in each model, and find perfect agreement with the exact results for the YL criticality in two dimensions. Using bosonization for the Schwinger model and the Polyakov-Hubbard transformation for the other models, we show that in all of these quantum models the YL critical point is described, as expected, by a massless bosonic field with an $i \phi^3$ interaction. In the quantum clock model, this critical field interacts with a massive bosonic field, and we identify the massless and massive states in the Hamiltonian spectrum. In addition, we numerically compute the two-point function of $\phi$ at the Yang-Lee critical point and show that it grows with distance, in agreement with theoretical expectations.

02.
arXiv (CS.LG) 2026-06-16

Incentives and Evidence in Learned Service Orchestration

arXiv:2606.16555v1 Announce Type: cross Abstract: Reinforcement learning for service orchestration has been the subject of sustained research for over a decade, yet it is not used in production at scale. The usual explanation is that learned controllers degrade under delayed and noisy telemetry, workload shifts, and uncontrolled tenants. We test whether existing evidence supports that explanation. We evaluate three highly influential RL-based orchestration systems spanning resource allocation, DAG scheduling, and autoscaling, using pre-registered predictions about comparative degradation under production-relevant perturbations and paired inference with family-wise error correction. Across the tests, most predicted performance reversals do not occur. Diagnostic analyses show that these outcomes often reflect comparator collapse, artefact limitations, or evaluation choices rather than evidence that learned controllers tolerate the perturbations. One apparent advantage under observation lag is roughly fortyfold compared to a Kubernetes HPA-equivalent controller. Another widely cited result cannot be reconstructed from its released artefact, and the strongest reproducible margin is far smaller than the published results. Conclusions also reverse under changes in perturbation magnitude and evaluation mode. Based on these results and broader patterns in the literature, we identify an institutional problem. Publication and review incentives favour benchmark gains against convenient comparators, even when those gains provide little evidence of deployment performance. We argue that the problem is not solely technical. Rather, it is institutional, so learned orchestration needs production-grade comparators, registered perturbation models, separate operational metrics, and publication criteria that reward reproducible operational evidence. Without these changes, the literature can grow without establishing whether learning improves orchestration.

03.
arXiv (CS.LG) 2026-06-11

APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations

arXiv:2606.11553v1 Announce Type: new Abstract: Generic time-series foundation models transfer poorly to wireless network telemetry whose signals are bursty, zero-inflated, and coupled across protocol layers. We present APEX, a network-native, decoder-only transformer for forecasting enterprise AP telemetry, and evaluate it on DHCP degradation as a representative network task. APEX is pre-trained on 10-channel multivariate telemetry from ~4,500 production wireless networks (~100K AP time series, 34 metrics per AP), and is available as APEX-Large (269M, cloud) and APEX-Edge (10.5M, edge). On a 192-step (4-day) DHCP degradation benchmark, APEX-Large reduces MAE by 18% over the strongest foundation-model baseline (Toto) and 38% over SARIMA, with anomaly-detection F1 = 0.93, while APEX-Edge enables sub-second, privacy-preserving inference on AP-class edge hardware. These results suggest network-native pre-training is a practical foundation for proactive wireless operations.

04.
Science (Express) 2026-05-07

Induction of broadly neutralizing HIV antibodies by a two-step mechanism informs vaccine design | Science

作者: 未知作者

A major obstacle confronting HIV-1 vaccine and cure research is the lack of an outbred animal model for rapid and consistent induction of broadly neutralizing antibodies (bNAbs). We designed an epitope-focused simian-human immunodeficiency virus (SHIV.5MUT) that elicited broad and potent V3-glycan-targeted antibodies within a year of infection in 14 of 22 macaques compared with 0 of 14 control animals. SHIV.5MUT elicited bNAbs by a two-step mechanism, inducing an initial wave of V1-directed antibodies that selected for Envs with shortened, hypoglycosylated V1 loops, which in turn primed V3-glycan bNAb precursors. Rhesus bNAbs were immunogenetically and structurally diverse, closely resembling human V3-glycan bNAbs. Env-bNAb coevolution revealed a diverse repertoire of bNAb precursors and the Env variants that matured them, yielding a molecular blueprint for vaccine design.

05.
arXiv (CS.CV) 2026-06-16

Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models

The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreeing with each other. Here, we propose Divide-and-Denoise, a method for coordinating multiple pre-trained diffusion models during sampling. Much like managing a specialized workforce, our method creates a fair but efficient division of labor across models. Central to our method is the notion of an allocation which defines the responsibility of each model to every region of the noisy sample. At every timestep, we then denoise by (i) updating the allocation by solving a fair division game, where we divide the sample into regions that maximize total utility under fairness constraints, and (ii) aligning the models with this allocation, where we guide each model to denoise within its assigned region. This leads to a new composite denoising process that evolves in tandem with a division process. We evaluate Divide-and-Denoise on conditional image generation. Across several quality metrics, including the GenEval benchmark, our method outperforms baselines and resolves common failures including missing objects and mismatched attributes. Experiments show that Divide-and-Denoise utilizes each model's expertise without neglecting any other model.

06.
arXiv (quant-ph) 2026-06-12

Quantum-Driven Neuromorphic Computing for Million-Qubit-Scale Workloads

arXiv:2606.12968v1 Announce Type: new Abstract: We introduce Apollo, a 10000 node p-qubit neuromorphic processor fabricated in 16 nm mixed signal CMOS and operating fully at room temperature with a typical analog core power envelope of about 0.5 W. Its fundamental element, the p-qubit, is a bistable stochastic unit whose continuous time state fluctuations are driven by integrated quantum entropy units that inject true quantum derived randomness. This enables ultrafast stochastic transitions at low energy while preserving a classical state representation. Apollo combines these p-qubits with a high degree Hyperion 256 interconnect topology, allowing efficient embedding of dense Ising and QUBO problems with substantially reduced minor embedding overhead compared with sparse annealing platforms. We show that, through the Suzuki Trotter correspondence, the equilibrium statistics and annealing dynamics of the p-qubit network reproduce key properties of transverse field quantum annealing without cryogenic cooling, long lived coherence, or microwave control. Beyond device level validation, Apollo is evaluated on a three dimensional spin glass benchmark previously used to study quantum advantage in superconducting annealers. Across 300 disorder realizations, Apollo reaches substantially lower ground state energies than reported cryogenic quantum annealing hardware, while remaining distinct from classical simulated annealing and simulated quantum annealing. A 350 nm release candidate device experimentally validates the core p-qubit dynamics, thermodynamic sampling correctness, and continuous time annealing behavior. These results establish Apollo as a room temperature, industrially scalable platform for quantum driven energy based optimization, probabilistic inference, generative modeling, and hybrid classical quantum workflows.

07.
arXiv (CS.CL) 2026-06-12

SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents

Language model agents are increasingly effective in solving realistic tasks through multi-turn tool use. However, training reliable tool-using agents remains challenging in practice. While reinforcement learning provides an on-policy paradigm for improving agents from their own environment interactions, its effectiveness depends heavily on the training task distribution. When tasks are fixed before training, the task distribution can become increasingly mismatched with the policy's evolving capabilities, causing many rollouts to be spent on uninformative tasks. We propose SENTINEL, a failure-driven reinforcement learning framework that turns the Solver's rollout failures into targeted training tasks. SENTINEL follows a Controller–Proposer–Solver loop: the Controller analyzes failed trajectories and summarizes recurring error patterns, the Proposer generates executable tasks that stress these weaknesses, and the Solver is trained on the targeted tasks. On Tau2-Bench Retail with Qwen3-4B-Thinking-2507, SENTINEL improves Pass\^{}1 from 66.4 to 74.9 and outperforms RL on general synthetic tasks across Pass\^{}k metrics. These results demonstrate that model failures provide an effective and scalable source of targeted training signal for improving tool-using language model agents.

08.
arXiv (CS.CV) 2026-06-12

Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning

While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidence acquisition and multi-step visual interaction. This limitation suggests that relying solely on implicit visual representations from vision encoders is insufficient for recovering fine-grained spatial evidence. We introduce PERception-Interaction-reason Agent (PERIA), a tool-augmented visual agent for spatial reasoning tasks across map reasoning, visual probing, and vision reconstruction. PERIA uses two lightweight tool families: vision perception tools for exposing textual, symbolic, and spatial evidence, and vision interaction tools for manipulating visual context, tracing paths, and verifying spatial relations. To train PERIA, we develop a unified recipe that combines supervised tool-use trajectory synthesis, composite rewards, and Observation-Relaxed Group-in-Group Policy Optimization (OR-GIGPO) for effective multi-tool behavior. Experiments on 13 benchmarks from 8 datasets show that PERIA-8B improves over the Qwen3-8B backbone by 10.0% on in-distribution benchmarks and 4.4% on out-of-distribution benchmarks, while outperforming previous state-of-the-art baselines of similar size by 7.0%-14.8%. It also achieves performance comparable to much larger models such as Qwen3-VL-235B-A22B-Thinking and GPT-5, demonstrating the effectiveness of PERIA in enhancing spatial reasoning capabilities.

09.
arXiv (CS.CL) 2026-06-24

One Year Later...The Harms Persist, But So Do We!

General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety safeguards remain inadequate and inconsistent across clinical conditions. This study evaluates six proprietary LLMs across 16 DSM-5 conditions using four adversarial attack variants, introducing an eight-dimension harm taxonomy and a multi-dimensional evaluation framework. Results show that safeguards hold reliably only for suicide and self-harm, while conditions such as eating disorders, substance use disorder, and major depressive disorder exhibit failure rates of up to 100%. We argue that ethical design and deployment of these LLMs demand clearly defined harm categories across clinical conditions and implementation of safeguards accordingly. Until such safeguards are in place, these models pose significant risks to vulnerable populations, making their growing integration into educational settings a particularly concerning.

10.
arXiv (CS.LG) 2026-06-24

PROTECT-90: A Fault Dataset for Power System Protection

arXiv:2606.24298v1 Announce Type: cross Abstract: The increasing interest in data-driven methods for power system protection is accompanied by a lack of standardized, publicly available high-voltage waveform datasets that enable transparent and reproducible evaluation. To address this gap, this paper introduces the PROTECT-90 dataset, an open electromagnetic transient (EMT)-simulated reference benchmark for high-voltage fault studies with consistent digital-fault-recorder-like measurements, publicly released with this work. The dataset comprises 9,022 physically consistent short-circuit simulation episodes generated on a standardized 90 kV double-line topology with systematically documented domain randomization of grid operating points, line parameters, and fault conditions. For each episode, synchronized three-phase voltage and current waveforms are recorded at eight measurement locations and released together with structured, machine-readable metadata describing fault type, fault location, inception time, and operating conditions. All modeling assumptions, parameter ranges, and data-generation procedures are explicitly documented to ensure transparency and cross-study comparability. By combining physically grounded EMT simulation, balanced scenario coverage, and open accessibility, PROTECT-90 establishes a standardized foundation for reproducible benchmarking of protection-oriented signal processing and learning-based methods.

11.
bioRxiv (Bioinfo) 2026-06-17

Correcting spatial transcriptomics data affected by a prevalent transcript leakage problem across platforms, species, and tissues

Spatial transcriptomics has been widely applied to study the spatial distribution of cell types, cell states, and specific gene expression in tissue samples. However, we show that there is a prevalent transcript leakage problem in spatial transcriptomics data, where transcripts expressed by a cell diffuse to its neighborhood and are recurrently detected in the nearby cells. By analyzing published data sets, we show that this problem is general across data produced from different tissues and different species using different imaging-based and sequencing-based spatial transcriptomics platforms. It affects both upstream tasks such as expression quantification as well as downstream tasks such as cell-type annotation and detection of spatially-dependent gene expression. To tackle the transcript leakage problem, we propose a reference-free Bayesian model-based method, DeLeakage, which cleans up the data much more effectively than existing denoising methods. DeLeakage also improves cell-type annotation and avoids false detection of spatially dependent expression.

12.
arXiv (CS.CL) 2026-06-15

Harsher on Male? Evaluating LLMs on Gender-Asymmetric Moral Framing Across Diverse Conflict Scenarios

Existing studies on gender bias in LLMs have largely focused on stereotypes, occupational associations, or explicit harmful outputs. In this work, we ask whether LLMs apply consistent response standards to the same negative behavior under matched male-actor and female-actor conditions. We introduce GAMA-Bench, a gender-mirrored benchmark of 1,298 scenarios covering intimate relationship and public social conflicts. It constructs gender-neutral misconduct templates through controlled grids and cross-model review, then compiles them into paired first-person prompts with matched actor-gender and role-reference variations. We further design a structured response-framing protocol to measure how models allocate punishment, empathy, escalation, instruction, and blame. Experiments on 10 representative LLMs reveal a consistent male-disadvantaging asymmetry: male actors receive more punitive, escalatory, and blame-centered framing, whereas female actors receive more therapeutic and empathy-oriented framing for the same misconduct. Further analyses show that this pattern persists across model families, scenario tracks, model scale, and explicit thinking-style reasoning. The official code is available at https://github.com/xufeiqiong/GAMA-Bench.

13.
Nature (Science) 2026-06-10

A 5.3-million-year-old deep-sea whale necropolis in the Diamantina Zone

Whale falls are biodiversity oases at seabeds1–6, yet their record from the oceans has remained sparse and fragmentary6,7. Here we report the discovery of a vast whale necropolis in the Diamantina Zone (4,616- to 7,001-m depth), extending about 1,200 km along the sea floor of the southeastern Indian Ocean. This area has a deep and extensive accumulation comprising five modern natural whale-fall communities and 476 fossil cetaceans recorded. We show that carcasses host specialized communities dominated by brittle stars, bone-boring worms and chemosynthesis-based bivalves and that the fossil record in this area comprises both extant and extinct deep-diving beaked whales. Isotopic dating shows that whale falls in this region have occurred since at least 5.3 million years ago. These findings reshape the understanding of the limits and biogeography of whale-fall ecosystems and establish some deep sea floors as a fossil archive for tracing cetacean evolution over geological time. Researchers uncovered an enormous deep-sea accumulation of whale remains in the southeastern Indian Ocean, showing long-term, specialized ecosystems and an extensive fossil record that offers new insight into deep-ocean biodiversity and whale evolutionary history.

14.
arXiv (CS.LG) 2026-06-17

A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise

arXiv:2606.18183v1 Announce Type: cross Abstract: Temporal difference (TD) learning with linear function approximation is a core method for policy evaluation. Its classical continuous-time description is an ordinary differential equation (ODE), which captures the asymptotic mean dynamics but neglects stochastic fluctuations determining the error floor. We introduce a stochastic differential equation (SDE) approximation for linear TD(0) under Markovian noise. The resulting model distinguishes the contraction dynamics governed by the projected Bellman operator from the influence of Markovian sampling. As a consequence, the model explains the constant-stepsize error floor through the interaction between Markovian long-run covariance and the contraction geometry of the projected Bellman operator.

15.
arXiv (CS.AI) 2026-06-12

GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns

arXiv:2606.12419v1 Announce Type: cross Abstract: Several educational domains rely heavily on diagrams and visual cues, yet most existing tutoring datasets are limited to text-only interactions. This limits the development of AI tutors that can teach in visually grounded ways used by human instructors. Thus, we introduce GeoDial, a multimodal tutoring dataset of over 1.3K teacher-student dialogs in the domain of geometry collected from experienced math teachers, where instructional turns are explicitly grounded in diagram highlights. We propose a scalable annotation protocol that integrates dialog acts, visual highlighting, and feedback, enabling fine-grained supervision of both language and visual tutoring behavior. To illustrate the challenges posed by this setting, we fine-tune several vision-language models on GeoDial and evaluate their ability to generate tutoring utterances and diagram highlights. While supervised fine-tuning substantially improves the quality of generated dialog, it struggles to produce accurate diagram highlights, revealing a key limitation of current methods and highlighting the need for approaches that more effectively integrate visual reasoning with pedagogical interaction.

16.
arXiv (CS.AI) 2026-06-16

A Definition of Good Explanations and the Challenges Explaining LLM Outputs

arXiv:2606.14838v1 Announce Type: new Abstract: How to define a good explanation is a long-standing philosophical debate which has found recent renewed interest in the context of AI outputs. Explainability is crucial for AI adoption in many contexts, but in order to produce good explanations of AI systems, we must first have an understanding of what good explanations are. In this paper we propose a definition inspired by the notion of counterfactual explanations, however we argue that one must also take into account the interlocutor's prior beliefs in each fact that could be offered in an explanation. We explore the ramifications of this definition for AI explainability and, in particular, why LLM outputs are difficult to produce good explanations for.

17.
arXiv (CS.AI) 2026-06-24

Fix Initial Programs and Iteratively Refine Repair Instructions Toward Non-Elimination Multi-Turn Program Correction

arXiv:2604.23989v2 Announce Type: replace-cross Abstract: Recent work on large language models (LLMs) has emphasized the importance of scaling inference compute. From this perspective, the state-of-the-art method Scattered Forest Search (SFS) has been proposed, employing Monte Carlo Tree Search with carefully crafted initial seeds and textual optimization for multi-turn program correction. However, its complexity makes it unclear what factors contribute to improvements in inference performance. To address this problem, we analyze SFS and propose a simpler method, \textsc{Iterative Refinement of Repair Instructions} (IRRI), which fixes initial programs and iteratively refines repair instructions. Because of the simplicity of IRRI, we theoretically establish the non-elimination of IRRI using Oracle-Guided Inductive Synthesis (OGIS). Experiments on several program generation benchmarks suggest that IRRI achieves inference performance comparable to state-of-the-art methods. These results indicate that, even without complex search structures, refining initial programs with high-quality repair instructions alone can effectively improve inference performance.

19.
arXiv (CS.CV) 2026-06-16

PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

6D object pose estimation, which predicts the transformation of an object relative to the camera, remains challenging for unseen objects. Existing approaches typically rely on explicitly constructing feature correspondences between the query image and either the object model or template images. In this work, we propose PoseGAM, a geometry-aware multi-view framework that directly predicts object pose from a query image and multiple template images, eliminating the need for explicit matching. Built upon recent multi-view-based foundation model architectures, the method integrates object geometry information through two complementary mechanisms: explicit point-based geometry and learned features from geometry representation networks. In addition, we construct a large-scale synthetic dataset containing more than 190k objects under diverse environmental conditions to enhance robustness and generalization. Extensive evaluations across multiple benchmarks demonstrate our state-of-the-art performance, yielding an average AR improvement of 5.1% over prior methods and achieving up to 17.6% gains on individual datasets, indicating strong generalization to unseen objects. Project page: https://windvchen.github.io/PoseGAM/ .

20.
medRxiv (Medicine) 2026-06-22

Regional Service-System Conditions Associated with Facility-Linked Home-Based Specialist Care in Japan: A Claims-Based Ecological Study of Home Dialysis

Background Complex chronic care is increasingly delivered in patients' homes while remaining linked to specialist facilities for training, monitoring, and backup care. Home dialysis provides a useful case because peritoneal dialysis (PD) and home hemodialysis (HHD) share a home-facility delivery structure but differ in technical and operational requirements. This study examined regional service-system conditions associated with the presence and scale of PD and HHD in Japan. Methods This ecological study used publicly available claims, administrative, census, and geospatial data harmonized to 334 Secondary Medical Areas. Regional indicators were organized into four domains: dialysis service delivery, implementation support for home-based care, hospital backup capacity, and living and sociodemographic context. Diffusion was examined using claims-based indicators of regional presence and post-presence scale, analyzed separately for PD and HHD with Firth penalized logistic regression and zero-truncated negative binomial regression, respectively. Results PD was observed in 271 regions and HHD in 109. Patterns of associated regional conditions differed by modality and stage. PD was associated mainly with existing dialysis-service organization, whereas HHD was associated with broader regional supports, including home-care delivery, living infrastructure, transition support, and hospital-system indicators. Conditions associated with presence differed from those associated with scale. Cross-modality associations suggested that shared regional factors may shape the distribution of both modalities. Conclusions Regional conditions for home dialysis diffusion in Japan differed by modality and stage. PD was linked mainly to existing dialysis-service organization, whereas HHD was linked to multi-domain regional support for technically demanding home treatment. Under standardized reimbursement, local service-system capacity may remain important for modality- and stage-specific diffusion of home dialysis.

21.
arXiv (CS.CL) 2026-06-16

Revisiting the Systematicity in Negation in the Era of In-Context Learning

Understanding the meaning of negated sentences remains one of the challenges for language models, even in the era of large language models (LLMs). We analyze systematicity regarding LLM understanding of negation from two perspectives: behavioral systematicity and representational systematicity. For behavioral systematicity, we confirm that through demonstrations and in-context learning, LLMs can recognize negation expressions and scope within sentences to some extent, but they fail to achieve perfect performance. In particular, the difficulty of the negation scope recognition for models varies depending on the output format. For representational systematicity, we analyze the extent to which function vectors can be robustly constructed from in-context examples for tasks that are essential to understanding negation. The experiments suggest that while function vectors can be composed for negation cue extraction tasks, extracting function vectors for recognizing scope is more challenging.

22.
arXiv (CS.CV) 2026-06-16

R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies

Spatial generalization is critical for imitation-learned manipulation policies, but achieving it typically requires scaling demonstrations across diverse object poses, robot configurations, and camera viewpoints. Data augmentation from a few source demonstrations offers a practical alternative to costly real-world collection. Simulation-based augmentation can create controllable variation, but requires complex environment and object setup and may introduce a sim-to-real gap. Recent real-to-real methods avoid these issues by jointly editing 3D observations and action trajectories from real demonstrations, yet they still rely on strong 3D scene parsing and geometry completion, and often produce observations tailored to 3D pointcloud policies rather than RGB-based 2D policies. We propose R2RDreamer, a real-to-real demonstration augmentation framework that preserves the geometric consistency of 3D action-observation editing while moving visual completion to 2D video space. Specifically, R2RDreamer first performs lightweight 3D augmentation by editing incomplete object pointclouds and end-effector trajectories in a shared 3D frame; it then projects the edited scene into masked image-space control videos with occlusion-aware reasoning and uses a dense-control image-to-video model to complete temporally coherent RGB observations. Experiments on spatially shifted manipulation tasks with both 2D diffusion-style policies and vision-language-action policies show that R2RDreamer improves spatial generalization from limited source demonstrations, with analyses validating the contributions of 3D editing, occlusion-aware projection, and video completion.

23.
medRxiv (Medicine) 2026-06-10

A Three-Tier Operational Benchmark for Evaluating Large Language Models on Hospital Medication Safety

Objective. To introduce PsiBench, a clinically validated medication-safety benchmark for evaluating large language models (LLMs) against the standards used to certify hospital computerized provider order entry (CPOE) and electronic health record (EHR) systems, and a non-overlapping three-tier evaluation framework separating highest-stakes discrimination, the operational CDS regime, and category-correct alerting. Materials and Methods. PsiBench comprises 492 medication-safety scenarios across 11 safety categories, created by clinical pharmacology experts whose work underpins an annualized testing procedure used by more than 2,000 U.S. hospitals. The three-tier framework partitions the scenarios non-overlappingly: Discrimination (98 scenarios, 50 fatal vs 48 deception, near-balanced 51%/49%); Operational (394 scenarios, 261 serious unsafe plus 133 safe including 41 Excessive Alerts reclassified as operational negatives); and Attribution (311 alert-required scenarios). We evaluated 40 frontier LLMs from 10 providers over 3 runs per scenario at temperature 0.2 (or the provider default where temperature is not configurable), yielding 59,040 evaluations conducted April 21-23, 2026. Results. Headline binary performance on the full benchmark spans a wide range across the 40 models: F1 78.5%-92.3%, accuracy 65.4%-89.8%, sensitivity 81.4%-100.0%, specificity 6.1%-81.8%. Leading models by F1 (o4-mini 92.3%; o3 92.2%) pair high sensitivity with meaningful specificity; three models saturate sensitivity at 100% but fall below 25% specificity, indistinguishable from a naive always-alert classifier. The wide spread on a single headline metric motivates tier-specific analyses, developed in a separate clinical paper. Discussion and Conclusion. PsiBench and the three-tier framework operationalize a rigorous evaluation rubric for LLM medication safety, grounded in two decades of national hospital audit experience. The framework generalizes to any binary medication-safety classifier (rule-based, conventional ML, or LLM-driven), supporting tier-aware model selection and post-deployment surveillance.

24.
arXiv (CS.AI) 2026-06-16

Shachi: A Modular, Controllable Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behavior

arXiv:2509.21862v3 Announce Type: replace Abstract: How collective behaviors emerge from the interactions of individual LLM-driven agents is a central question in artificial life, yet controlled study of these emergent dynamics has been hindered by the lack of a principled simulation framework for systematic experimentation. To address this, we introduce Shachi, a principled methodology and modular framework that decomposes an agent's cognition into core components: Configuration for intrinsic identity, Memory for contextual continuity, and Tools for extended capabilities, all orchestrated by an LLM reasoning engine. This decomposition treats each cognitive component as an independently controllable variable, enabling perturbation studies that trace how micro-level cognitive traits propagate into population-level dynamics. We investigate behavioral patterns across a 10-task benchmark spanning three levels of collective complexity. Shachi enables memory transfer across environment transitions, producing history-dependent behavioral shifts, and allows agents to simultaneously inhabit multiple environments, revealing cross-environment interference invisible in single-environment studies. Furthermore, in a real-world U.S. tariff shock case study, locally interacting agents with individually controlled cognitive components produce macro-level market dynamics directionally consistent with observed real-world outcomes. Our work provides a rigorous, open-source simulation framework for LLM-based ABM, aimed at fostering cumulative scientific inquiry into the emergent collective behaviors of interacting artificial agents.

25.
Nature (Science) 2026-06-12

An innovative technology boosts image quality for protein structures

After years of effort, two research teams have developed ‘laser phase plate’ systems that could help cryo-electron-microscopy users to generate high-quality structures for a broad range of proteins. After years of effort, two research teams have developed ‘laser phase plate’ systems that could help cryo-electron-microscopy users to generate high-quality structures for a broad range of proteins.