Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
PLOS Computational Biology 2026-06-17

Deciphering cell type-specific causal genetic effects on brain imaging-derived phenotypes and disorders with single-cell Mendelian randomization

Authors:

by Anyi Yang, Xingzhong Zhao, Xing-Ming Zhao, Yucheng T. Yang Reconstructing causality routes from genetic effects to complex phenotypes in particular cell types is crucial for understanding biological mechanisms underlying the brain-associated phenotypes including imaging-derived phenotypes (IDPs), and brain disorders and behaviors (DBs). Here, we develop a single-cell Mendelian randomization framework to infer cell type-specific causal relationships between gene expression and diverse brain-associated complex phenotypes by integrating single-cell expression quantitative trait loci (cis-eQTLs) and genome-wide association study findings. We identifiy a set of 254 and 217 cis-eQTL target genes (eGenes) that may have causal effects on 112 IDPs and 26 DBs in eight cell types, respectively. These causal eGenes exhibit strong cell type specificity and varied pleiotropy among different types of brain-associated phenotypes. Further integrative analysis reveals putative causality routes among cell type-specific causal eGenes and brain-associated complex phenotypes. Finally, we characterize the spatiotemporal expression patterns of these causal eGenes, and highlight the coordinated associations of the brain-associated phenotypes based on the expression of their causal eGenes. Overall, our study presents a large-scale analysis of the genetic effects of brain structures, disorders and behaviors, providing a catalog of cell type-specific causal eGenes.

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

Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework

The rapid rise in LLM capabilities has made AI agents increasingly viable across a broad range of tasks. Among the most promising applications is building production-ready customer-facing agents, a challenge that demands coordinated excellence in evaluation methodology, context engineering, training, and online measurement. Yet these critical pillars are typically developed in isolation, creating blind spots that only surface after deployment. In this paper, we present a unified framework that bridges offline development with online impact for customer support AI agents at Nubank, a company with 100M+ users. Our approach integrates several key components: (1) structured context engineering tailored to customer support agents, (2) systematic human-in-the-loop prompt iteration, (3) rigorous LLM judge evaluation with measured inter-rater agreement and GEPA optimization for consistency, and (4) ideation-to-production validation. A central insight is that evaluation-pipeline quality directly determines iteration velocity. We present results from five production deployments spanning distinct domains: card delivery, debt management, credit-limit support, card management, and product explanation. These deployments deliver consistent customer-satisfaction gains while substantially accelerating iteration. In our card-delivery deployment, large-scale A/B testing yields a 37 percentage-point improvement in AI transactional Net Promoter Score and a 29 percentage-point gain in self-service rate over prior agent variants, alongside a strong correlation between offline simulation metrics and online outcomes, demonstrating that eval-driven development reliably predicts production impact. On most use cases, AI satisfaction reaches within a few percentage points of expert human agents.

03.
bioRxiv (Bioinfo) 2026-06-18

pykarambola: Minkowski tensor morphometry of 3D structures

Three-dimensional biological morphologies encode functional and physiological state, yet the directional, orientational, and topological properties of these shapes are rarely captured by morphometric tools available for bioimage analysis. Minkowski tensors are mathematically rigorous tensor-valued measures that encode surface curvature and directionality for objects of arbitrary topology, with tensor eigensystems that directly quantify elongation axes and anisotropy. A C++ implementation, karambola, computes Minkowski tensors for triangulated surfaces but is inaccessible within Python-based bioimage workflows. Here we present pykarambola, a pip installable Python package that accepts NumPy arrays and standard mesh formats and returns Minkowski tensors, including derived anisotropy and orientation quantities. A high-level label-image API converts 3D integer arrays into per-object Minkowski tensors in a single call, making pykarambola directly compatible with the output of widely used segmentation tools. An optional Cython extension accelerates graph-traversal steps of mesh initialization for large-scale analyses. Benchmarked on 1,584 adrenal gland meshes, pykarambola reproduces all 121 C++ karambola output features to near-floating-point agreement and, in the pure-Python build, is 2.8x faster at 28^3 and 1.5x faster at 64^3 voxel resolution, with speedups primarily attributable to karambola's sequential per-object file I/O. pykarambola is freely available as an open-source software package.

04.
arXiv (CS.LG) 2026-06-12

Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling

arXiv:2606.13347v1 Announce Type: new Abstract: Diffusion models have emerged as state-of-the-art generative models for high-fidelity image synthesis, particularly in their classifier-free guided and classifier-guided forms. However, standard classifier guidance concentrates probability mass around high-density class mean, leading to poor coverage of rare samples in the tails of the class-conditional distributions. Recent work on diffusion-based tail sampling mitigates this by training an additional low-density-seeking classifier with a synthetic-vs-real discriminator, at the cost of additional networks and training. In parallel, a number of samplers and distillation techniques accelerate or refine diffusion sampling, but do not explicitly address long-tail coverage. We propose a purely sampling-time, density-aware extension of classifier-guided conditional diffusion model that targets low-density regions without any additional training. We have applied guidance at noisy images not on predicted noise like most diffusion models. Starting from a pretrained conditional diffusion model and classifier on ImageNet, we modify the guided reverse dynamics by steering trajectories toward low-confidence regions via the modified classifier gradient, and at each time step, we also guide the sampling process toward the predicted real image. 1st guidance helps explore low-probability samples, and 2nd guidance helps to generate samples to be close to the real data manifold. The proposed sampler consistently improves ADM model recall at 64x64 resolution while maintaining a comparable FID, and with a 256x256 ADM model, we showed the results visually with different combinations of both guidance. We also showed that standard ADM classifier guidance, combined with predicted real image guidance, helps generate high perceptual quality samples with a 256x256 ADM model on ImageNet.

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

HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents

Long-horizon agents rely on memory mechanisms to compress interaction history, but optimizing memory writing faces a distinct credit assignment challenge: a memory update may be rewarded or penalized due to downstream tool failures, noisy observations, or reasoning errors rather than its own contribution. This causally entangled credit can lead agents to discard useful evidence or preserve irrelevant information. We propose HiMPO, a Hindsight-Informed Memory Policy Optimization framework for assigning less-entangled credit to memory-writing actions in long-horizon agents. HiMPO first estimates the local utility of a memory update by comparing the task-relevant information recoverable from the previous and updated memories under the same pre-write state. It then uses hindsight relevance as a bounded retrospective filter that attenuates memory credit when local utility is not supported by the target outcome. The resulting memory-specific advantage is applied only to memory tokens, while trajectory-level rewards optimize the rest of the agent behavior. Across judge-based open-domain tasks and objective compressive-memory QA, HiMPO improves over strong memory-based and RL-based baselines while preserving compressed-context efficiency. Controlled interventions further show that HiMPO reduces blame leakage from tool-induced errors and improves attribution fidelity of memory updates.

06.
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.

07.
arXiv (CS.LG) 2026-06-18

N(CO)$^2$: Neural Combinatorial Optimization with Chance Constraints to Solve Stochastic Orienteering

arXiv:2606.18514v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) offers a promising alternative to traditional heuristic-based methods for solving complex graph optimization problems by proposing to learn heuristics through data. This class of problems frequently arises in automation, as it can be used to model a variety of applications. While NCO has been extensively studied for deterministic combinatorial optimization problems, there are only a few works that aim to solve stochastic combinatorial optimization problems. In this work, we present N(CO)$^2$: Neural Combinatorial Optimization with Chance cOnstraints to solve the Stochastic Orienteering Problem (SOP) without the use of hand-crafted heuristics. By integrating a reinforcement learning (RL) framework, the model optimizes path selection under uncertainty, effectively balancing exploration and exploitation. Empirical results demonstrate that our method generalizes well across diverse SOP instances, achieving competitive performance compared to the state-of-the-art mixed-integer linear program (MILP) for the task. The proposed approach reduces human effort in heuristic design while enabling adaptive and efficient decision-making in uncertain environments.

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

Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models

Latent reasoning models (LRMs) replace explicit chain-of-thought with continuous thoughts. Recent work treats observable latent-state patterns, such as BFS-like frontiers and decodable arithmetic computation, as evidence for internal reasoning mechanisms. Evaluating two LRMs (Coconut and CODI) against controls lacking the proposed recurrence or curriculum, we find these patterns also appear in the controls and do not always causally affect behavior. Causal interventions reveal that latent-thought utilization is not binary but graded, scaling with a thought's causal effect on model behavior. Geometric analyses reveal this effect concentrates in low-rank directions whose step-to-step geometry grows more structured as their behavioral influence increases. Latent thoughts should therefore be treated as hidden computation, not hidden explanation: decodability, attention, or static structure alone cannot establish mechanism. LRM interpretability thus requires matched controls and causal tests.

09.
arXiv (CS.LG) 2026-06-18

Identifying Structural Biases from Causal Mechanism Shifts

arXiv:2606.18834v1 Announce Type: new Abstract: Causal discovery methods commonly assume that all data is independently and identically distributed (i.i.d.) and that there are no unmeasured variables affecting the system. In practice, these assumptions are often violated, leading to inaccurate inference. In this paper, we study how to identify hidden confounding and selection biases from causal mechanism shifts. In particular, we show that structural biases lead to dependent mechanism shifts. That is, by considering for which variables the mechanisms change given data from different environments, we can tell which variables are unbiased, which are subject to hidden confounding, and which are undergoing selection bias. We formalize this into an empirically testable criterion based on mutual information, and show under which conditions it identifies structural biases. To tell which nodes are subject to what kind of bias, we introduce the StruBI algorithm. Experiments on synthetic and real-world data show that StruBI works well in practice, accurately recovering affected variable sets and types of biases, outperforming the state-of-the-art by a wide margin.

10.
arXiv (CS.LG) 2026-06-11

Bergson: An Open Source Library for Data Attribution

arXiv:2606.11660v1 Announce Type: new Abstract: Data attribution is a promising field in interpretability that aims to explain model behavior through the influence of its training data, with applications including debugging undesirable model behavior and training dataset curation. However, significant engineering effort is required to perform it at scale, and many cutting edge techniques lack open-source tooling and support. Bergson is an open source library that aims to enable faster progress in the field by providing a host of techniques that scale to very large language models and pre-training datasets. The library natively supports on-disk gradient stores and multi-node distributed training, and provides quality of life tools for researchers. Finally, we introduce the first open-source implementations of three leading data attribution methods: MAGIC, SOURCE, and TrackStar. The library is available at https://github.com/EleutherAI/bergson .

11.
arXiv (quant-ph) 2026-06-19

Frequency-Multiplexed Millimeter-Wave Fault-Tolerant Superconducting Qubits Enabled by an On-Chip Nonreciprocal Control Bus

arXiv:2512.17588v2 Announce Type: replace Abstract: Scaling superconducting quantum processors is fundamentally limited by the escalating complexity of cryogenic wiring and the detrimental effects of microwave crosstalk and Purcell decay. This paper proposes a novel architecture based on frequency-multiplexed millimeter-wave superconducting qubits, integrating an on-chip cryogenic nonreciprocal space-time-periodic Josephson frequency multiplier as a universal control bus. The bus replaces multiple high-frequency XY drive lines with a single low-frequency input tone, which is parametrically converted into a comb of high-order harmonics, each resonantly addressing a distinct qubit. The nonreciprocal nature of the bus provides intrinsic isolation that suppresses Purcell decay and reduces coherent crosstalk by more than $98\%$ compared to a conventional reciprocal shared drive line. Full error-budget analysis demonstrates that the architecture can maintain gate errors below the fault-tolerance threshold for arrays exceeding 25 qubits, converting a crosstalk-dominated error budget into one primarily limited by intrinsic material coherence. Theoretical modeling based on a non-Markovian master equation further indicates that the engineered environment enables information backflow, offering a pathway to enhanced coherence. This integrated, frequency-multiplexed, and nonreciprocal control bus offers a compelling route toward dramatic I/O simplification, improved noise resilience, and scalable high-coherence superconducting quantum processors.

12.
medRxiv (Medicine) 2026-06-17

The interaction between chronic hepatitis B (CHB) and Metabolic dysfunction-associated steatotic liver disease (MASLD) in a diverse central London population

Introduction: The overlap between chronic hepatitis B (CHB) and metabolic dysfunction-associated steatotic liver disease (MASLD) is an emerging global health challenge. We investigated the impact of MASLD and metabolic comorbidity in a diverse London viral hepatitis clinic. Methods: This retrospective cross-sectional study (May 2018-Feb 2024) included adults with CHB having controlled attenuation parameter (CAP) measurements. MASLD was defined as CAP >264 dB/m plus [≥]1 cardiometabolic factor (CMF). We used univariable and multivariable models to examine MASLD's relationship with liver stiffness and hepatitis B viral load (HBV VL). Results: Among 323 individuals (67% male, median age 36), most were from Black (35%) or non-white British/Irish (29%) backgrounds. Overall, 64% had [≥]1 CMF, and 20% had MASLD. The CHB/MASLD group was significantly older (median 43 vs 35 years, p

13.
arXiv (CS.CL) 2026-06-11

Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical judgment while patients increasingly use them for health advice. We show this assumption is fragile: when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer. We call the ability to maintain correct judgment under adversarial context epistemic resilience, and introduce MedMisBench to measure it. MedMisBench contains 10,932 medical question items and 48,889 misleading context-option pairs spanning medical reasoning, agentic capability, and patient-journey evaluation. Across 11 model configurations, mean accuracy falls from 71.1% on original questions to 38.0% under focused misleading context, with 51.5% attack success. The most damaging injections are formal, rule-like fabrications: authority-framed falsehoods reach 69.5% attack success and exception-poisoning claims reach 64.1%. A 14-member clinical panel from 7 countries identified serious potential harm in 38.2% of reviewed cases. MedMisBench exposes a structural blind spot in LLM evaluation in medical settings: existing benchmarks measure what models know, but not whether they preserve correct medical judgment under misleading context.

14.
medRxiv (Medicine) 2026-06-22

Midlife Measures of General Cognitive Performance in the National Longitudinal Study of Adolescent to Adult Health (Add Health)

Objective: The Add Health Cognitive Assessment, Physical, and Sensory Function Protocol (Add CAPS) was developed to assess cognitive, physical, and sensory function in early midlife in a nationally representative sample in the United States. Using Add CAPS, we developed two general cognitive performance measures. Methods: The sample included 2,525 participants from Add Health Wave VI who completed an in- home assessment of cognitive performance. Confirmatory factor analysis (CFA) was used to derive two general cognitive performance (GCP) scores: (1) a five-domain score based on originally designed cognitive domains (Add CAPS GCP), and (2) a modified score aligned with the Harmonized Cognitive Assessment Protocol (HCAP) framework (Add CAPS GCP-H). We evaluated model fit using Root Mean Square Error of Approximation (RMSEA), Standardized Root Mean Square Residual (SRMR), and Comparative Fit Index (CFI) and tested factor scores for criterion validity. Results: Both models showed good fit (Add CAPS GCP: RMSEA = 0.025, SRMR = 0.031, CFI = 0.968; Add CAPS GCP-H: RMSEA = 0.027, SRMR = 0.033, CFI = 0.962), indicating that they adequately represent the underlying GCP construct. Discussion: The Add CAPS cognitive battery captures a robust, hierarchical structure of GCP across alternative domain specifications. The derived factor scores provide a valuable method for characterizing a person's cognitive baseline during midlife. Importantly, the Add CAPS GCP-H enhances comparability with the HCAP network, supporting cross-cohort analyses of cognitive aging.

15.
arXiv (CS.CL) 2026-06-17

Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication

Two recent studies (Jones et al. (2026); Zeng et al. (2026)) reach apparently contradictory conclusions about whether LVLMs can coordinate on efficient referring expressions. We control for task differences between the studies while directly comparing their prompting styles. We replicate the finding that models can coordinate efficient referring expressions when explicitly prompted to do so, suggesting that other task differences are not responsible for divergent results. However, we also find that the same models fail to infer the need for communicative efficiency from a more implicit prompt, highlighting critical differences between how humans and AI systems communicate.

16.
medRxiv (Medicine) 2026-06-12

Microbial etiology, antibiotic susceptibility profiles, and multidrug resistance of urinary tract infections at a secondary healthcare facility in Ghana

Background: Rising antibiotic resistance challenges empirical therapies for urinary tract infections (UTIs). This study evaluated the microbial etiology, susceptibility profiles, and multidrug resistance (MDR) patterns of uropathogens among outpatients at the Berekum Holy Family Hospital, Ghana. Methods: This cross-sectional study (February to August 2021) screened 263 symptomatic outpatients. Mid-stream urine samples underwent quantitative culture, biochemical identification, and antimicrobial susceptibility testing via the Kirby-Bauer disc diffusion method following the 2021 CLSI guidelines. Results: Significant bacteriuria prevalence was 22.8% (60/263). UTIs predominated in females (78.3%, 47/60; p = 0.1501) and individuals [≥]45 years (33.3%, 20/60). Gram-negative rods accounted for 90.0% of isolates, primarily Escherichia coli (26.7%), Citrobacter spp. (25.0%), and Enterobacter spp. (21.7%); Staphylococcus aureus (10.0%) was the only Gram-positive pathogen. Extreme phenotypic resistance was observed against piperacillin/tazobactam (98.3%), cefotaxime (93.3%), tetracycline (88.3%), and cefoperazone (85.0%). Conversely, highest therapeutic susceptibilities were retained by amikacin (78.3%), levofloxacin (61.7%), and gentamicin (58.3%). Conclusion: The high prevalence of MDR uropathogens against advanced beta-lactamase inhibitor combinations and cephalosporins necessitates an immediate re-evaluation of regional empirical protocols. Amikacin, levofloxacin, and gentamicin remain viable options prior to culture confirmation. These findings establish a crucial phenotypic baseline to guide localized prescribing policies and regional antimicrobial resistance tracking strategies.

17.
arXiv (CS.LG) 2026-06-19

Weibull Weight-Scale Parameter Evolution under AdamW Training Dynamics

Authors:

arXiv:2606.19367v1 Announce Type: new Abstract: Building on a two-parameter Weibull framework for diagnosing transformer weight distributions, we study why the Weibull weight-scale parameter $\lambda$ grows, overshoots, and then relaxes during AdamW training. We derive a leading-order three-force decomposition of the squared weight norm from the AdamW update: an alignment force measuring the correlation between weights and the adaptive update direction, an injection force from adaptive step magnitude, and a decay force from decoupled weight decay. On self-trained Pythia-70M models with ground-truth optimizer moments, alignment dominates the rise phase, contributing 88-94% of the absolute force budget across four random seeds and remaining robust to super-weight removal. Near saturation, alignment and decay approach balance, explaining the transition from weight-scale growth to relaxation. These force dynamics directly govern the squared-norm component underlying $\lambda(t)$; the remaining RMS-to-Weibull reconstruction offset is measurable and decomposes into bridge and integration components, totaling approximately 5-6% in densely sampled regions. To extend the analysis to real models where optimizer moments are unavailable, we introduce a spline displacement method that recovers the alignment force from sparse checkpoints with approximately 92-94% accuracy, about twice the naive two-point baseline. We further observe that the peak value of $\lambda(t)$ varies with training-data coherence in our experiments, suggesting a data-dependent component of weight-scale growth that we leave to a controlled follow-up study. Code and data are available at https://github.com/tiexinding/NPM-Weibull-public.

18.
arXiv (CS.AI) 2026-06-17

A Machine-Learned Comorbidity Index

arXiv:2606.17450v1 Announce Type: new Abstract: Traditional comorbidity scores (e.g., Charlson and Elixhauser) are widely used for risk adjustment and patient stratification, but they have two key limitations: (i) they are largely mortality-centric and do not align well with other clinical outcomes, and (ii) their linear, rule-based structure cannot capture nonlinear, outcome-specific risk relationships. We propose a Machine-Learned Comorbidity Index (MLCI) that maps diagnosis codes to a single scalar by maximizing the normalized Hilbert-Schmidt Independence Criterion (nHSIC) between the learned score and multiple clinical outcomes. MLCI captures nonlinear risk-outcome dependence and is supported by a theory that characterizes when a unified, informative admission-level ordering can be achieved across outcomes. Empirical results on multiple benchmark electronic health record (EHR) datasets show that MLCI outperforms strong baselines across multiple evaluation metrics.

19.
arXiv (CS.LG) 2026-06-11

Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems

arXiv:2606.12337v1 Announce Type: cross Abstract: Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based optimization, while physics-informed neural networks (PINNs) have emerged as a flexible alternative. Their relative performance remains difficult to assess because the two approaches are often compared under different formulations, parameterizations, optimizers, and regularization choices. We present a fair comparison of adjoint optimization and PINNs for PDE-constrained inverse problems. From a common abstract formulation, we instantiate both methods on identical domains, governing equations, observation models, and regularization terms, while matching the optimizer, unknown parameterization, and arithmetic precision wherever applicable. The benchmarks include unsteady Burgers, noisy Darcy permeability inversion, three-dimensional Allen–Cahn reaction identification, and unsteady Navier–Stokes viscosity identification. The results show that the representation of the unknown largely determines the preferred method: grid-based fields favor the discrete adjoint, whereas neural representations are native to PINNs and relevant for closure and constitutive modeling. For time-dependent problems, adjoint inversion can be dominated by trajectory storage and differentiation, while PINNs provide satisfactory reconstructions at lower cost. A PINN-warm-started adjoint strategy then recovers adjoint-level accuracy at substantially reduced cost.

20.
arXiv (CS.AI) 2026-06-17

WallZero: Mastering the Game of WallGo with Strategic Analysis

arXiv:2606.17847v1 Announce Type: new Abstract: WallGo is a recently introduced strategic board game popularized by the 2025 Netflix series The Devil's Plan. Although played on a small 7 x 7 board, its combination of stone movement and wall placement yields high game-tree complexity and intricate strategic interactions. Despite its growing popularity, WallGo remains underexplored. This paper presents WallZero, an AlphaZero-based agent for the two-player WallGo setting. We introduce tailored action and feature designs to improve playing performance significantly. In the evaluation, WallZero defeats two professional Go players who participated in this study, securing on average 1.98x more territory per game. Beyond its strength, we use WallZero to assess game fairness and identify key strategies for mastering WallGo. Interestingly, our results show that the opening used in the Netflix series yields a more balanced game. Our code is available at https://rlg.iis.sinica.edu.tw/papers/wallzero.

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

Parallel Test-Time Scaling with Multi-Sequence Verifiers

arXiv:2603.03417v2 Announce Type: replace-cross Abstract: Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it is hindered by two key bottlenecks: accurately selecting the correct solution from the candidate pool, and the high inference latency from generating many full solutions. We argue that both challenges are fundamentally linked to verifier calibration, as a well-calibrated verifier improves answer selection and enables early-stopping strategies to reduce latency. However, existing non-generative verifiers are limited as they score each candidate in isolation, overlooking rich contextual information across the set of candidates. To address this, we introduce the Multi-Sequence Verifier (MSV), a lightweight verifier that predicts each candidate's correctness conditioned on the full sampled set. MSV achieves improved calibration, which directly enhances best-of-N selection performance and empowers a novel early-stopping framework. Across challenging mathematical reasoning benchmarks, MSV improves best-of-64 accuracy by up to 6\% relative to strong baselines, and in the early-stopping setting reaches the same accuracy as baselines with less than half the latency.

22.
arXiv (CS.AI) 2026-06-19

FFinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming

arXiv:2606.19887v1 Announce Type: cross Abstract: Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation. We introduce FinRED, an expert-guided red-teaming framework for financial LLM safety evaluation developed with financial experts. FinRED uses a novel two-level taxonomy mapping global standards (e.g., FATF and EU DORA) to threats ranging from regulatory evasion to complex fraud, integrated with a scalable pipeline that converts real financial documents into context-rich red-teaming Behavioral Prompts (seeds) through an expert-defined schema. Rigorous expert validation confirms seed plausibility and realism for meaningful LLM safety evaluation. We also provide an expert-validated, finance-specific rubric that goes beyond disclaimer checks, aligns more closely with human experts than static one-size-fits-all rubrics, and reduces critical false negatives from 28 to 12. Aligned with internationally adopted risk-management and information-security standards (e.g., ISO/IEC 27001), FinRED is deployed in South Korea's Financial Security Institute (FSI) regulatory sandbox for generative AI security evaluation in real financial services. To mitigate dual-use risks, the dataset, generation pipeline, prompt template, and evaluation framework are gated for qualified researchers at https://github.com/selectstar-ai/FinRED-paper and https://huggingface.co/datasets/datumo/FinRED.

23.
Nature Medicine 2026-06-08

Post-adjuvant chemotherapy in ctDNA-positive patients with resected colorectal cancer: a randomized phase 3 trial

Authors:

Tumor-informed circulating tumor DNA (ctDNA) enables detection of molecular residual disease (MRD) after curative resection of colorectal cancer (CRC), but whether early intervention improves outcomes remains uncertain. ALTAIR was a randomized, double-blind, phase 3 trial embedded in the CIRCULATE-Japan platform evaluating a post-adjuvant ctDNA surveillance strategy with treatment initiation upon molecular recurrence. Patients with resected stage 0–IV CRC who became ctDNA positive after completion of standard-of-care therapy and had no radiological evidence of disease were randomly assigned (1:1) to receive trifluridine/tipiracil (FTD/TPI) or placebo for 6 months. The primary endpoint was investigator-assessed disease-free survival (DFS). Between July 2020 and June 2023, 243 patients were randomized to FTD/TPI (n = 122) or placebo (n = 121). Median DFS was 9.30 months with FTD/TPI and 5.55 months with placebo (hazard ratio = 0.79, 95% confidence interval: 0.60–1.05, P = 0.107), and the primary endpoint was not met. FTD/TPI increased grade 3 or higher hematologic adverse events (73.0% versus 3.3%) without new safety signals. These findings indicate that post-adjuvant intervention with FTD/TPI did not significantly improve DFS in ctDNA-positive patients without radiological disease. ClinicalTrials.gov identifier: NCT04457297 . In the randomized, double-blind phase 3 ALTAIR trial, patients with resected colorectal cancer who became positive for circulating tumor DNA during post-adjuvant surveillance received trifluridine/tipiracil hydrochloride therapy, which did not significantly prolong disease-free survival compared with placebo.

24.
arXiv (CS.LG) 2026-06-18

On the Residual Scaling of Looped Transformers: Stability and Transferability

arXiv:2606.18524v1 Announce Type: new Abstract: Looped (weight-tied) Transformers apply a shared residual block $N$ times ($h \leftarrow h + \varepsilon\,f(h)$, same $f$ at each step), increasing effective depth without adding parameters. Prior depth-scaling analyses prescribe $\varepsilon = 1/\!\sqrt{L}$ for depth-$L$ residual networks. We show that this is insufficient for looped architectures: weight sharing makes residual updates correlated across iterations, requiring the stronger scaling $\varepsilon = 1/N$. For multi-layer blocks ($L$ unique layers looped $N$ times), we derive a factored parameterization $\varepsilon = \lambda/(N\!\sqrt{L})$ that separates the two sources of growth: $1/N$ controls the within-layer loop correlation, and $1/\!\sqrt{L}$ controls the across-layer variance. A key consequence is that the optimal learning rate depends only on the number of unique layers $L$, not on the loop count $N$, enabling direct hyperparameter transfer from small to large $N$ without retuning. Experiments on looped Transformers confirm that $1/N$ scaling improves trainability and yields better loss than $1/\!\sqrt{N}$ scaling across loop counts.

25.
arXiv (CS.AI) 2026-06-12

CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation

arXiv:2606.13513v1 Announce Type: new Abstract: Driven by conservative over-provisioning to guarantee service reliability, resource utilization in cloud data centers remains at low levels. To mitigate this, the forecast-then-optimize paradigm has emerged to optimize consolidation by anticipating future demands. While emerging time series foundation models promise to enhance this paradigm through zero-shot generalization, existing benchmarks focus solely on prediction error metrics. The actual decision utility of these advanced models remains unverified, rendering their practical value for downstream tasks uncertain. To bridge this gap, we propose CloudCons, a comprehensive end-to-end benchmark designed to evaluate forecasting models within the specific context of cloud resource consolidation. We build high-quality datasets that cover diverse workloads from Huawei Cloud, Microsoft Azure, and Google Borg, capturing distinct service characteristics ranging from synchronized diurnal rhythms to stochastic, pulse-like bursts and high-frequency noise. We conduct an extensive evaluation of statistical, deep learning, and foundation models. Our experiments reveal a pivotal finding: while foundation models demonstrate superior zero-shot forecasting accuracy, this advantage does not inherently translate into better decision utility. Of practical significance, we systematically analyze how the selection of predictive quantiles acts as a critical lever. We provide actionable guidelines for calibrating these selections to balance the trade-off between resource efficiency and service reliability, offering vital insights for real-world deployment decisions.