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.
arXiv (CS.CL) 2026-06-18

LegalWorld: A Life-Cycle Interactive Environment for Legal Agents

Civil litigation is inherently a life-cycle process: what a lawyer drafts on day one constrains what unfolds at trial months later. Yet existing legal benchmarks evaluate isolated subtasks, and prior legal-agent simulators reinitialize each scenario from shared ground truth, leaving cross-stage causal dependencies unmodeled. We present LegalWorld, a life-cycle interactive environment that models Chinese civil litigation as a causally connected state chain of five stages (seven sub-scenarios), grounded in 75,309 paired Chinese civil judgments. We pair it with reusable infrastructure (local memory, global case memory, a Skill/Tool library) that keeps each dispute consistent across its full life cycle. Building on this environment, we construct LongJud-Bench to evaluate agent capability across all five connected stages. 18,992 ratings from 217 legal-background evaluators confirm that LegalWorld trajectories are procedurally faithful and role-consistent; and a capability-level cross-model evaluation reveals sharp divergences that aggregate scores cannot expose, with no single backbone leading across consultation, drafting, and courtroom advocacy. Detailed resources will be released publicly.

02.
arXiv (CS.LG) 2026-06-12

Feature-preserving Latent-EnKF for Data Assimilation of Flows with Shocks

arXiv:2606.12559v1 Announce Type: cross Abstract: The ensemble Kalman filter (EnKF) is widely adopted for sequential data assimilation, but fails for solutions with discontinuities, such as shocks in compressible flows. Uncertainty in shock location induces multimodal ensemble statistics that violate the Gaussian assumptions underlying the EnKF, producing large-scale spurious oscillations in the analysis state. We introduce a feature-preserving latent-EnKF that performs the ensemble update in a learned low-dimensional latent space, where shock and flow features admit a smooth manifold representation, thereby preserving sharp features during EnKF analysis. The updated latent state is mapped back to physical state through a shared decoder for all ensemble members. The algorithm eliminates the member-specific ordered training and positivity flooring used in prior approaches. Numerical experiments on a Sod shock tube and Mach 2 shock interaction with a 2D cylinder, using sparse and noisy observations, show accurate feature recovery of shocks and contact discontinuities without spurious oscillations.

03.
arXiv (CS.AI) 2026-06-15

Generative AI for Managerial Decision-Making under Ambiguity and Sycophancy

arXiv:2603.03970v2 Announce Type: replace Abstract: Generative artificial intelligence (GenAI) is increasingly being integrated into complex business workflows, fundamentally shifting the boundaries of managerial decision-making. However, the reliability of its strategic advice in ambiguous business contexts remains a critical knowledge gap. To address this gap, this study compares multiple GenAI models in their ability to detect ambiguity, examines whether a systematic ambiguity-resolution process improves response quality, and investigates their susceptibility to sycophantic behavior when confronted with flawed managerial directives. Using a novel four-dimensional business ambiguity taxonomy, we conducted a human-in-the-loop experiment across strategic, tactical, and operational scenarios. The resulting decisions were assessed through a human-validated automated evaluation framework based on agreement, actionability, justification quality, and constraint adherence. The results show that our approach not only distinguishes different types of ambiguity, but also reveals how ambiguity resolution systematically changes model behavior. In particular, resolving ambiguities improved decision quality across all managerial levels, with the strongest gains observed in constraint adherence. The analysis further showed that sycophantic behavior is not uniform across models: some models challenged flawed assumptions, whereas others tended to comply with them. This study contributes to the bounded rationality literature by positioning GenAI as a cognitive scaffold that can detect and resolve ambiguities managers might overlook, while demonstrating that its artificial limitations require human oversight to ensure its reliability as a strategic partner.

04.
arXiv (math.PR) 2026-06-15

Semiclassical limit of Polyakov-Liouville measure and Q-Curvature Uniformization on evev-dimensional manifolds

arXiv:2606.14443v1 Announce Type: new Abstract: We study the semiclassical limit of the Polyakov-Liouville measure $\boldsymbol{\nu}_\gamma$, which is a non-Gaussian measure on $H^{-\eps}(M)$ that has recently been extended from Riemann surfaces to general Riemannian manifolds $(M,g)$ of even dimension. We show that under an appropriate rescaling in the semiclassical limit as $\gamma\to0$, the normalized Polyakov-Liouville measure $\Q_\gamma$ concentrates on the unique smooth weight $u$ for which the conformal metric $e^{2u}g$ on $M$ has constant $Q$-curvature.

05.
arXiv (CS.CL) 2026-06-18

SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding

Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks. However, their ability to reliably reason from gene-level knowledge to functional understanding, a core requirement for knowledge-enhanced cell atlas interpretation, remains largely underexplored. To address this gap, we introduce SciHorizon-GENE, a large-scale gene-centric benchmark constructed from authoritative biological databases. The benchmark integrates curated knowledge for over 190K human genes and comprises more than 540K questions covering diverse gene-to-function reasoning scenarios relevant to cell type annotation, functional interpretation, and mechanism-oriented analysis. Motivated by behavioral patterns observed in preliminary examinations, SciHorizon-GENE evaluates LLMs along four biologically critical perspectives: research attention sensitivity, hallucination tendency, answer completeness, and literature influence, explicitly targeting failure modes that limit the safe adoption of LLMs in biological interpretation pipelines. We systematically evaluate a wide range of state-of-the-art general-purpose and biomedical LLMs, revealing substantial heterogeneity in gene-level reasoning capabilities and persistent challenges in generating faithful, complete, and literature-grounded functional interpretations. Our benchmark establishes a systematic foundation for analyzing LLM behavior at the gene scale and offers insights for model selection and development, with direct relevance to knowledge-enhanced biological interpretation.

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

Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding

arXiv:2606.18101v1 Announce Type: new Abstract: Graphical user interface (GUI) grounding requires vision-language models (VLMs) to identify small target elements in high-resolution screenshots and predict precise screen coordinates. On-policy self-distillation (OPSD) is a promising post-training approach for this coordinate-sensitive task, since it provides dense token-level teacher signals beyond hard coordinate labels. However, naive OPSD is not well suited to GUI grounding: OPSD evaluates the teacher on student-generated prefixes, the quality of coordinate-token teacher signals can degrade when the prefix has already deviated from the target coordinate, leading to unreliable teacher signal. To mitigate this, We propose quality-aware self-distillation for VLM-based GUI grounding, which improves coordinate-token teacher-signal quality through soft correctness-aware gating and teacher-probability scaling. The soft correctness-aware gate checks whether the teacher's current coordinate-token prediction can still be completed into the ground-truth box under the student-generated prefix. If not, the corresponding teacher signal is down-weighted. Teacher-probability scaling then uses the teacher's confidence as a lightweight factor to further calibrate the strength of the gated supervision. A key empirical finding is that neither component alone improves overall performance, whereas combining them consistently improves performance. This suggests that the two mechanisms play complementary roles: correctness-aware gating suppresses unreliable coordinate-token supervision, while teacher-probability scaling calibrates the strength of the remaining signals. Experiments across six GUI grounding benchmarks show that our method consistently improves the base model and outperforms strong baselines.

07.
arXiv (CS.CV) 2026-06-16

VigilFormer: Deformable Attention for Video Anomaly Detection with Causal Risk Inference

Authors:

Video anomaly detection in surveillance settings must balance detection accuracy against real-time throughput, a tension that existing methods address either through stronger feature extractors or more efficient architectures, but rarely both. We present VigilFormer, a unified framework that combines deformable spatio-temporal attention with causal temporal modeling to detect anomalies in untrimmed surveillance video. The proposed Deformable Spatio-Temporal Encoder (DSTE) attends to a sparse set of informative locations across frames, avoiding the quadratic cost of dense attention while retaining the ability to capture irregular motion patterns. A Causal Anomaly Classifier (CAC) applies dilated causal convolutions over snippet-level features and optimizes a contrastive multiple-instance learning objective that separates anomalous and normal representations without frame-level labels. To meet deployment constraints, an Adaptive Confidence Scheduler (ACS) dynamically skips low-information frames at inference time, reducing redundant computation in static scenes. Evaluated on UCF-Crime, ShanghaiTech, and CUHK Avenue, VigilFormer achieves AUC scores of 87.83%, 97.21%, and 89.74% respectively, at 41.5 FPS on a single GPU, outperforming recent weakly-supervised methods in both accuracy and speed.

08.
arXiv (CS.LG) 2026-06-18

OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing

arXiv:2606.19149v1 Announce Type: cross Abstract: Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approaches such as fuzzing require substantial infrastructure and often target narrow classes of bugs. Recent advances in large language models (LLMs) enable semantic reasoning about program behavior, but applying LLMs to repository-scale security analysis introduces challenges related to context management, cost, and verification. We present OpenAnt, an open-source vulnerability discovery system that integrates static program analysis with LLM-based reasoning in a multi-stage pipeline. OpenAnt introduces three key techniques. First, codebases are decomposed into self-contained analysis units filtered by reachability from external entry points, reducing the analysis surface by up to 97% while preserving attack-relevant code. Second, candidate vulnerabilities undergo adversarial verification through constrained attacker simulation, where the model evaluates exploitability under realistic attacker capabilities. Third, findings are validated through dynamic verification, in which exploit environments are generated automatically, executed in sandboxed containers, and discarded after use. Evaluation on widely used open-source projects including OpenSSL, WordPress, and Flowise shows that this architecture can identify previously unknown vulnerabilities while maintaining manageable analysis cost and substantially reducing false positives. Our results suggest that closed-loop vulnerability discovery pipelines, combining semantic reasoning with exploit validation, provide a practical path toward scalable automated security analysis. OpenAnt is released as open source under the Apache 2.0 license at https://github.com/knostic/OpenAnt.

09.
arXiv (CS.AI) 2026-06-12

Can I Buy Your KV Cache?

Authors:

arXiv:2606.13361v1 Announce Type: new Abstract: Right now, across the world, AI agents are repeating the same absurd act: to read one document, they each recompute it from scratch. Every agent re-runs prefill, the most compute-intensive step a large model takes, over identical text, only to rebuild a key-value (KV) cache identical to the one the agent before it just built. The same answer, computed a million times. We make a proposal that is almost offensively simple: compute it once. Let a publisher precompute a document's KV cache, and let every other agent buy the right to load it and skip prefill. It works, and it is token-exact: loading a precomputed KV and continuing matches prefilling from scratch (24/24 greedy tokens, and at the logits level), with no accuracy cost. On Qwen3-4B, reuse is 9-50x cheaper in compute than prefill, and the gap widens with length (prefill's attention scales with L^2), so a single reuse already pays it back. Then the part that matters: where the KV lives. Shipping it fails, because KV is nearly incompressible, so per-load egress costs more than the prefill it saves. Hosting it provider-side, exactly as production prompt-caching works, removes egress entirely. The size of the prize is set by our measured compute saving: serving one hot 3774-token document to 80M agents costs ~$1.5M to re-prefill but only ~$0.03M of reuse compute (49.7x less). The 0.1x cache-read tariff APIs charge passes a 10x discount to users while sitting inside this measured envelope, so the 10x is a floor that the measured ~50x compute saving clears, and the gap to the physical ~50x is provider margin: millions of dollars per popular document. We frame the resulting agent-native prefill CDN and leave lossless KV compression and a cross-party payment layer as the open problems.

10.
arXiv (CS.CV) 2026-06-16

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

Instruction-based image editing has made notable progress with recent advances in generative models. However, the quality of the edited result is still influenced by the randomly sampled initial noise, particularly in complex editing scenarios. An unsuitable initial noise may lead to unsatisfactory editing results. Recent inference-time scaling methods address this issue by sampling multiple initial noises and selecting better candidates. Nevertheless, most of them follow a decode-then-verify scheme which introduces an efficiency-accuracy trade-off. When decoding is performed after limited inference steps, the decoded images often remain too noisy for reliable assessment, whereas sufficiently denoised images require much higher computational cost. To address this issue, we propose VeriLatent, a plug-and-play adaptive inference-time scaling framework with early-step latent verification for image editing. Specifically, we propose a novel verifier that scores each initial noise through a latent-space editing activation map at an early stage. It identifies promising candidates by assessing whether they can induce an effective edit in the correct region. This enables efficient early pruning without decoding latents into images. Building on this, we further develop an adaptive search strategy for inference-time scaling. It allocates inference budgets according to editing difficulty, thereby reducing the number of function evaluations (NFE). Extensive experiments on multiple benchmarks and different base models demonstrate that VeriLatent consistently improves both editing performance and inference-time scaling efficiency.

11.
arXiv (CS.CL) 2026-06-12

G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents

While Large Language Models (LLMs) have advanced open-domain dialogue systems, maintaining long-term consistency remains a challenge due to inherent limitations in long-context reasoning and the inefficiency of processing extensive raw text. Existing approaches typically rely on either unstructured memory storage, which is prone to information loss, or computationally expensive LLMs that incur high latency. To address these limitations, we propose G-Long, a graph-enhanced framework that utilizes a fine-tuned small Language Model (sLM) for structured triplet extraction and associative retrieval, significantly reducing operational costs. Furthermore, we introduce the novel attention-aware importance scoring mechanism that leverages the intrinsic cross-attention signals of a T5 summarizer to identify salient memories. Extensive experiments across diverse benchmarks demonstrate that G-Long achieves state-of-the-art performance in both response generation and memory retrieval, yielding performance gains of up to 9.8% in response quality on MSC and 40.8% in retrieval recall on LME, while significantly minimizing computational overhead.

12.
arXiv (math.PR) 2026-06-17

Optional Stopping for Superhedging Supermartingales

arXiv:2606.17452v1 Announce Type: new Abstract: Superhedging supermartingales, introduced by the authors in previous work, are non-probabilistic processes defined via subadditive outer integrals that carry a purely financial interpretation in terms of superhedging cost. Building on the Leinert-König theory of non-lattice integration, the present paper establishes several results that are classical in probability theory but whose non-probabilistic proofs require fundamentally new arguments: (i) a tower inequality for the conditional outer integral \overline{\sigma}_j applied at stopping times, reducing to equality when the integrand is conditionally integrable; (ii) three versions of Doob's optional stopping theorem, organised by the class of supermartingale and the range of the stopping times; and (iii) Dubins' upcrossing inequality in both finite- and infinite-time horizons. A key structural result, property (K)-a.e., identifies conditions under which the two superhedging operators \overline{\sigma}_j and \overline{I}_j coincide on non-negative functions, extending the scope of all preceding results to the positive operator \overline{I}_j. None of the proofs invoke classical measure-theoretic tools; in particular, (classical) integrability and measurability are not assumed. The analogues of classical stochastic results acquire a purely financial interpretation and, in this way, gain depth and generality by providing a context that is independent of any a priori probabilistic structure.

13.
arXiv (CS.AI) 2026-06-16

Learning Interface Breakup: A Geometry-Conditioned Latent Surrogate for Spray Formation

arXiv:2606.16587v1 Announce Type: cross Abstract: Designing spray nozzles requires predicting how geometry shapes transient two-phase breakup, but high-fidelity volume-of-fluid (VOF) simulations with adaptive mesh refinement (AMR) are too expensive for iterative design exploration. Standard surrogate models are also challenged by this setting because both the liquid–gas interface and the underlying adaptive discretization evolve across time and geometries. We introduce a geometry-conditioned latent surrogate trained on 797 two-phase nozzle simulations that addresses this by encoding the AMR cell-density field, rather than the full multi-channel flow state, as a compact proxy for where the solver concentrates resolution. From this representation, the model reconstructs transient density evolution and nozzle geometry, and a lightweight second stage recovers the remaining flow variables. On held-out simulations, the method accurately captures key interface dynamics while reducing inference time to 0.045 seconds per trajectory, corresponding to a speed-up of more than $6\times10^4$ relative to Basilisk CFD. These results suggest that AMR refinement structure can serve as a compact and learnable representation for geometry-conditioned surrogate modeling of transient two-phase flows.

14.
bioRxiv (Bioinfo) 2026-06-13

Virus-human protein-protein interactions predict viral phenotypes

Viral phenotypes such as host and tissue tropism are critical determinants of viral infection and transmission. Inferring viral phenotypes presents unique challenges compared to cellular organisms, as viruses rely entirely on host machinery for replication and survival. Current methods for predicting viral phenotypes mainly rely on viral genomic data, often overlooking host-related information. Here, we evaluated the utility of predicted virus-human protein-protein interactions (PPIs) in inferring diverse viral phenotypes using machine-learning algorithms. For predicting human infectivity, a PPI-based machine learning model outperformed both virus genomic and protein sequence-based models that used large language model embeddings. It also surpassed previous methods that incorporated both viral and host genomic data. The human proteins identified by the model were significantly enriched in functions related to viral infection and immune response. In predicting various phenotypes of human RNA viruses, PPI-based models performed better than virus sequence-based models in forecasting virulence, human transmissibility and transmission routes, while showing comparable performance to genomic sequence-based models in predicting tissue tropism. Finally, we demonstrated that a PPI-based model could distinguish high-risk HPV genotypes from low-risk ones. Proteins associated with high-risk HPV were involved in apoptosis and immune regulation, whereas those linked to low-risk HPV were enriched in telomere maintenance and DNA repair. Collectively, this study is the first to demonstrate the value of predicted virus-human PPIs in inferring viral phenotypes, thereby enhancing our understanding of the molecular mechanisms underlying these phenotypes. It also provides effective tools for risk assessment of emerging viruses, contributing to improved pandemic preparedness.

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

SAM-Deep-EIoU: Selective Mask Propagation for Multi-Object Tracking

Multi-object tracking has a heavy-tailed difficulty distribution: most frames are easy for a lightweight base tracker, while a small fraction are intrinsically hard. Video object segmentation (VOS) models can often preserve identity through the hard frames where the base tracker fails, but they are much more expensive in compute and memory. We propose selective mask propagation, a tracking algorithm that dispatches from a base tracker to a VOS model only on windows where an assignment-uncertainty signal fires. The base tracker's output is modified only when the VOS model makes a confident prediction that contradicts the base tracker's identity assignment; weak or inconclusive predictions preserve the base output. The method is training-free, treats both the base tracker and the VOS model as black boxes, and can benefit from replacing the VOS component with a more capable model. On DanceTrack, selective mask propagation improves three different base trackers. On SportsMOT, where identity preservation is central to sports analytics, SAM3-Deep-EIoU with global track association achieves state-of-the-art performance on the benchmark with 86.8 HOTA.

16.
arXiv (CS.AI) 2026-06-18

HAARES Half-Split Residual Basis Routing for Deep Transformers

Authors:

arXiv:2606.06564v2 Announce Type: replace-cross Abstract: Block-level residual routing makes learned residual aggregation practical by routing over block summaries, but each summary compresses an ordered sequence of attention and MLP updates into one cumulative vector. We propose \method{}, a lightweight residual basis router that keeps the cumulative block source and adds one half-split detail basis, computed as the difference between first-half and second-half residual updates. The detail basis is RMS-matched and updated online, exposing coarse intra-block trajectory information without dense sublayer-level routing. Across OpenWebText, cross-domain character-level benchmarks, and BPE-tokenized OpenWebText, the empirical pattern is depth-dependent: gains are small or mixed at shallow depth and most reliable in 48-layer models. In the 201M 48-layer setting, \method{} improves over Block AttnRes across all three seeds, while a 453M two-seed probe shows the same direction. Ablations rule out source duplication, random signed details, fixed detail-source biases, or block-count changes alone. Cost analysis shows that the method is FLOP-light but not wall-clock-free: it adds memory and routing overhead, yet its relative arithmetic cost is amortized as width grows and earlier convergence can reduce time-to-target.

17.
medRxiv (Medicine) 2026-06-10

Trajectories of brain structure and function in young adult carriers of genetic frontotemporal dementia variants

Background and Objectives: Converging evidence hints at neurodevelopmental effects in genetic frontotemporal degeneration (FTD). In cross-sectional studies, for some genes, young adult FTD variant carriers show differences in brain volumes and cognition compared to familial non-carriers. However, longitudinal trajectories may more sensitively capture FTD-related neurodevelopmental vs. neurodegenerative changes than cross-sectional approaches. This study examined longitudinal trajectories of brain volumes, executive function, and plasma biomarkers in young adult carriers compared to familial non-carriers, as measures of neurodevelopmental and neurodegenerative outcomes of FTD-causing variants. Methods: This longitudinal cohort study comprised participants, aged 18-30 years, from the FTD Prevention Initiative across Europe, Canada, and the USA. Genetic groups included C9orf72 (47%), MAPT (30%), and GRN (23%). Linear mixed-effects models were computed to assess longitudinal outcomes across age between groups, controlling for sex, scanner (for brain volumes), and education (for executive function); random effects accounted for between-subject variability nested within family membership. Results: Variant carriers (n=147) and familial non-carriers (n=113) did not differ in age (mean{+/-}SD, 25.9{+/-}3.2 years), sex (53% female), or number of visits (2.1{+/-}1.7). Young adult C9orf72 repeat expansion carriers exhibited smaller thalamic volumes than non-carriers at the reference age of 26 years (b=-982.8mm3, SE=317.0, p=0.0046, f2=0.32), with relatively stable trajectories across ages 18-30 (i.e., no change over time). Trajectories of rostral anterior cingulate volumes differed in C9orf72 carriers and non-carriers across age, where carriers showed relatively stable trajectories and non-carriers showed age-appropriate declines (b=64.4mm3, SE=29.9, p=0.035, f2=0.07). For MAPT and GRN, there were little to no differences in total brain, cortical, or subcortical volumes between groups and over time. No longitudinal differences were observed between carriers and non-carriers in executive function, or plasma NfL or GFAP for any genetic group. Discussion: C9orf72 repeat expansions were linked to smaller average thalamic volumes and stable trajectories between ages 18 to 30, supporting potential neurodevelopmental origins. The modest evidence supporting an absence of difference in neurodegenerative biomarkers and executive function suggests minimal early neurodegeneration and functional preservation in young adulthood.

18.
arXiv (CS.AI) 2026-06-16

Gaming-Resistant Insurance Contracts for Autonomous AI Agents: Strategy-Proof Toll Mechanism Design

arXiv:2606.16326v1 Announce Type: cross Abstract: Paper A defines a time-consistent actuarial runtime that prices each side-effect-bearing action against a contractually fixed safe default and gates execution against a reserve budget. It treats the operator as passive. This paper makes the operator strategic. We characterise a five-attack space for autonomous AI-agent insurance contracts and prove when the actuarial runtime is gaming-resistant. Two attack surfaces – post-toll safe-default selection and within-boundary action splitting – are closed by Paper A's minimal-authority and no-splitting clauses. The remaining three require new contract clauses. First, common-control aggregation prevents cross-boundary re-routing from reducing toll below the boundary potential applied to total exposure. Second, interface failures such as invalid JSON are contract-relevant events, not safety wins: treating them as zero-toll safe defaults can reward unreliable models, while escalation fees reverse the incentive. We validate this interface-compliance theorem on committed cross-model traces from the companion empirical paper. Third, a model-identity menu with a componentwise-minimum penalty schedule makes truthful reporting of the deployed model weakly dominant. We then compose these clauses with Paper A's runtime guarantees to obtain joint incentive compatibility over the five-attack space. Finally, a two-parameter premium family discharges operator individual rationality and weak budget balance at the truthful equilibrium. The result is an incentive-compatibility layer for actuarial control of autonomous-agent side effects.

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

Is Code Better Than Language for Algorithmic Reasoning

arXiv:2606.15589v1 Announce Type: cross Abstract: For tool-augmented language models, comparing natural-language reasoning with code-execution pipelines is difficult because the comparison changes both the intermediate representation and the execution mechanism. We separate these factors with an intermediate intervention: the model expresses its reasoning as executable code, and the language model simulates that code in context to produce an answer. On a 40-task verifiable algorithmic benchmark, deterministic code execution outperforms natural-language reasoning by +31.6pp. We observe that the intermediate intervention is not meaningfully different from natural-language reasoning (+0.15pp). These results suggest that, in our evaluated setting, changing the intermediate representation alone does not explain the tool-use advantage, providing evidence for the performance gains requiring reliable external execution. We formalize this intuition with a simple statistical decision-theoretic model that characterizes when execution dominates end-to-end risk in our disentangled trace-generation/execution regime. We validate our theory using a reconstruction intervention that leverages a proxy language model to infer natural-language reasoning traces from code representations, recovering performance comparable to the original natural-language reasoning pipeline. All experiments are at https://github.com/TerryTong-Git/ToolProj.

20.
arXiv (CS.CL) 2026-06-19

Toward Human-Centered AI-Assisted Terminology Work

Generative AI is likely to transform terminology work by creating new opportunities for automation. At the same time, it raises concerns about the future of terminologists and terminological resources, as efficiency pressures may encourage excessive automation based on the perception that human expertise can be replaced by AI. However, large language models remain unreliable for terminological purposes due to errors, hallucinations, and various forms of bias, making terminologists indispensable for ensuring the accuracy and reliability of terminological data. This paper argues that human-centered AI, an approach that emphasizes that AI's primary goal should be to contribute to human well-being, provides a framework for maximizing the benefits of generative AI while mitigating its risks. It contends that high levels of automation and meaningful human control are compatible and desirable, and that AI should enhance terminologists' capabilities while preserving their agency and decision-making authority. The implications of AI-assisted terminology work are examined through three interrelated dimensions: the augmented terminologist, ethical AI, and human-centered design. In particular, the paper examines how AI integration reshapes the role of the terminologist, affects professional values and working conditions, requires the management of AI-generated bias, and calls for the design of AI tools around the terminologist's needs. The paper concludes that a human-centered orientation is necessary to ensure that AI strengthens, rather than undermines, the essential role of terminology work in supporting specialized communication and the accurate transmission of knowledge across languages and cultures.

21.
arXiv (CS.AI) 2026-06-18

AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework

arXiv:2606.18532v1 Announce Type: cross Abstract: AI systems are increasingly evaluated in bounded environments that combine isolation, simulation, instrumentation, supervision, and evidence capture. For physical AI, AIoT, and cyber-physical systems, this shift is not a matter of terminology: the system under test may sense, decide, actuate, communicate, and fail through physical processes, networked devices, and human operators. This article develops an assurance-oriented account of AI sandboxes as controlled environments for testing, evaluation, verification, and validation across digital AI, embodied autonomy, and cyber-physical deployments. We formalize the sandbox boundary and a weakest-link rule for composing per-dimension evidence into a bounded deployment claim; separate major sandbox archetypes; define a cyber-physical threat model that includes attacks on the assurance apparatus itself; and introduce a measurement framework spanning fidelity, controllability, observability, containment, reproducibility, and governance artifacts, instantiated on three worked case studies of real sandboxes. The resulting threat model, taxonomy, and measurement framework clarify what a sandbox can validly test, which risks it can contain, and what forms of evidence it can support for safety, security, and regulatory assurance.

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

WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization

Recent text-to-image generation models have demonstrated remarkable capabilities in synthesizing highly realistic images from text inputs alone. Although existing benchmarks can evaluate the generation capabilities of various models to some extent, they struggle to comprehensively and accurately measure performance across multiple dimensions, often failing to reveal the inherent deficiencies of models in specific categories. To address these limitations, we propose WeGenBench, a novel benchmark designed for the comprehensive, multi-perspective evaluation of text-to-image generation capabilities. Our benchmark comprises a total of 4,000 test prompts across two primary categories, meticulously balanced between Chinese and English to evaluate bilingual and cross-cultural generation capabilities. Beyond macroscopic scene classification, we annotate each prompt with multi-dimensional tags tailored to the distinct content and challenges of each language, thereby refining the generation tasks into more specific sub-categories. Through a cross-dimensional evaluation mechanism leveraging both scene classifications and multi-dimensional tags, WeGenBench can precisely pinpoint model shortcomings in specific generation categories. Furthermore, to measure generation quality more accurately, we design and validate several novel evaluation metrics by integrating Vision-Language Models (VLMs), which assess model performance on domain-specific tasks from three core aspects. Crucially, our approach yields both the assessment outcomes and the detailed reasoning trajectories, facilitating a rigorous verification of the accuracy and soundness of the evaluation results. Finally, we conduct systematic benchmarking on current state-of-the-art methods and provide an in-depth analysis of the limitations present in existing models.

23.
arXiv (CS.LG) 2026-06-24

Polaris: A Godel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair

arXiv:2603.23129v3 Announce Type: replace Abstract: Gödel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, a Gödel agent for compact models that performs policy repair via experience abstraction, turning failures into policy updates through a structured cycle of analysis, strategy formation, abstraction, and minimal code pat ch repair with conservative checks. Unlike response level self correction or parameter tuning, Polaris makes policy level changes with small, auditable patches that persist in the policy and are reused on unseen instances within each benchmark. As part of the loop, the agent engages in meta reasoning: it explains its errors, proposes concrete revisions to its own policy, and then updates the policy. To enable cumulative policy refinement, we introduce experience abstraction, which distills failures into compact, reusable strategies that transfer to unseen instances. On MGSM, DROP, GPQA, and LitBench (covering arithmetic reasoning, compositional inference, graduate-level problem solving, and creative writing evaluation), a 7-billion-parameter model equipped with Polaris achieves consistent gains over the base policy and competitive baselines.

24.
bioRxiv (Bioinfo) 2026-06-14

Cellfm-datasets: A Unified Data Infrastructure for Single-Cell and Spatial Transcriptomics Foundation Model Pretraining

Large-scale cell foundation models are increasingly limited not only by model architecture, but also by the data infrastructure required to repeatedly sample sparse transcriptomic profiles from out-of-core cohorts. AnnData/H5AD has become a standard exchange format for single-cell and spatial omics analysis, yet its HDF5-backed layout is not designed for high-frequency random mini-batch loading under multi-worker and distributed pretraining. We present Cellfm-datasets, a data infrastructure artifact that converts H5AD cohorts into a self-describing compressed sparse row (CSR) memmap layout and exposes the resulting corpus through Hugging Face Dataset and IterableDataset interfaces. The artifact stores a shared gene vocabulary, per-sample metadata, optional spatial coordinates, observation metadata, manifests, and checksums, and reconstructs sparse cell or group records at runtime without dense expansion. A unified sampling abstraction supports random-cell groups, manifest-defined biological regions, and coordinate-based spatial blocks, with deterministic sharding across distributed ranks and data-loader workers. Spatial demonstrations on P14 mouse brain transcriptomics sections illustrate region- and block-level sampling over real anatomical structures. In controlled benchmarks on a public heterogeneous ModelScope scRNA-seq subset, Cellfm-datasets reached 60,571 +/- 1,734 samples/s in single-core random loading, scaled to approximately 160,000 samples/s with eight workers, and maintained near-constant process-private memory while reading up to one million cells. By moving sparse single-cell and spatial corpora from model-specific loader code into reusable, validated, and framework-native dataset artifacts, this design may reduce the engineering burden of reproducible cell foundation model pretraining and make repeated training runs, model comparisons, and mixed-modality data reuse easier to standardize.

25.
medRxiv (Medicine) 2026-06-18

Chest X-Ray as a critical screening tool for Household Contacts of TB: Lessons from Three Years of Programmatic Data in India

Introduction: Household contacts (HHCs) of pulmonary TB patients remain at high risk for TB infection and disease progression, yet many remain asymptomatic and are missed by symptom-screening pathways. While India expanded its TB preventative guidelines to include all HHCs in 2021, chest X-ray (CXR) screening continues to be used selectively, representing a missed opportunity in early case detection. Methods: The analysis uses programmatic data from Project JEET 2.0 (Joint Effort for Elimination of Tuberculosis), implemented by the William J. Clinton Foundation in India, between October 2021 and March 2024. Eligible HHCs (>=5 years) were offered CXR screening as part of TB preventive therapy (TPT) evaluation. Descriptive and multivariable analyses examined predictors of CXR uptake and TB yield. A two-stage logistic regression model estimated potential TB yield under universal CXR coverage. Model performance was evaluated using the area under the curve (AUC), and bootstrap simulations generated counterfactual estimates of missed TB cases. Results: Among 1,034,621 HHCs, 1.02% individuals were found positive for TB, which includes 7,786 HHCs who were on TB treatment already, while an additional 2,812 were identified during pre-TPT evaluation. Among eligible HHCs (n = 1,026,835), 70% were screened with CXR, of which 2.4% had suggestive TB findings. Of these, 79% went for further TB assessment. Symptomatic HHCs were more likely to be CXR screened (84% vs 69%) and assessed for TB, yet two-thirds of all detected TB cases were asymptomatic. It is estimated that universal CXR coverage and TB testing for suggestive cases can increase TB detection by at least 87%. Conclusion: The study provides a scalable approach to expand CXR coverage through public-private partnerships, enabling early TB detection among HHCs, especially among asymptomatic contacts. Future implementations will benefit from integrating AI-enabled reading, along with systematic follow up for those with suggestive findings.