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) 2026-06-17

Tungsten Germanide Superconducting Nanowire Single-Photon Detectors with Saturated Internal Detection Efficiency at Wavelengths up to 29 {\mu}m

arXiv:2511.20868v2 Announce Type: replace-cross Abstract: Superconducting nanowire single-photon detectors (SNSPDs) are among the most sensitive single-photon detectors available and have the potential to transform fields ranging from infrared astrophysics to molecular spectroscopy. However, extending their performance into the mid-infrared spectral region - crucial for applications such as exoplanet transit spectroscopy and vibrational fingerprinting of molecules - has remained a major challenge, primarily due to material limitations and scalability constraints. Here, we report on the development of SNSPDs based on tungsten germanide, a novel material system that combines high mid-infrared sensitivity with compatibility for large-scale fabrication. Our detectors exhibit saturated internal detection efficiency at wavelengths up to 29 {\mu}m, while using 2.7x thicker films (8 nm vs 3 nm) and up to 4.5x wider nanowires (360 nm vs 80 nm) compared to mid-infrared-optimized SNSPDs fabricated from tungsten silicide. This advance will enable scalable, high-performance single-photon detection in a spectral region that was previously inaccessible, opening new frontiers in remote sensing, thermal imaging, environmental monitoring, molecular physics, and astronomy.

02.
medRxiv (Medicine) 2026-06-17

Nickel and Dimed: How a Common Earth Element is Short-Changing Our Health

Nickel has been studied for a long time as an environmental contaminant but less so in its connection to population health. It does not announce itself as loudly as its transition metal brethren like mercury and cadmium, but its chemical properties permit it to be deleterious as a low-dose, chronic exposure, particularly among those with immune systems sensitized to it. There is a growing evidence base and vocabulary to discuss nickel's affect on health. However, in the U.S., there are not recent, reliable estimates of the share of the population with a nickel allergy, let alone how much nickel Americans are exposed to through their diet. This paper seeks to close this evidence gap by creating a new dataset of dietary nickel and other heavy metal exposure and assessing how high levels of dietary nickel exposure shape local demand for health care services. We use soil data from the U.S. Geological Survey and data on agricultural product transport from FoodFlows.org to create a county-level dietary nickel exposure index. We then use a large electronic health record database and double machine learning to estimate how demand for primary care services varies across levels of dietary nickel exposure. We find that counties with high nickel exposure experience an increase in the share of primary care office visits for symptoms highly suggestive of nickel poisoning. This result survives multiple hypothesis test corrections and placebo tests. Our research suggests that nickel has harmful effects on individual health whose exposure can be measured at a population level, and is shaping primary care across the U.S.

03.
arXiv (quant-ph) 2026-06-15

Who can compete with quantum computers? Lecture notes on quantum inspired tensor networks computational techniques

arXiv:2601.03035v2 Announce Type: replace Abstract: This is a set of lectures on tensor networks with a strong emphasis on the core algorithms involving Matrix Product States (MPS) and Matrix Product Operators (MPO). Compared to other presentations, particular care has been given to disentangle aspects of tensor networks from the quantum many-body problem: MPO/MPS algorithms are presented as a way to deal with linear algebra on extremely (exponentially) large matrices and vectors, regardless of any particular application. The lectures include well-known algorithms to find eigenvectors of MPOs (the celebrated DMRG), solve linear problems, and recent learning algorithms that allow one to map a known function into an MPS (the Tensor Cross Interpolation, or TCI, algorithm). The lectures end with a discussion of how to represent functions and perform calculus with tensor networks using the "quantics" representation. They include the detailed analytical construction of important MPOs such as those for differentiation, indefinite integration, convolution, and the quantum Fourier transform. Three concrete applications are discussed in detail: the simulation of a quantum computer (either exactly or with compression), the simulation of a quantum annealer, and techniques to solve partial differential equations (e.g. Poisson, diffusion, or Gross-Pitaevskii) within the "quantics" representation. The lectures have been designed to be accessible to a first-year PhD student and include detailed proofs of all statements.

04.
arXiv (quant-ph) 2026-06-17

The Standard Model, The Exceptional Jordan Algebra, and Triality

作者:

arXiv:2006.16265v2 Announce Type: replace-cross Abstract: Jordan, Wigner and von Neumann classified the possible algebras of quantum mechanical observables, and found they fell into 4 "ordinary" families, plus one remarkable outlier: the exceptional Jordan algebra. We point out an intriguing relationship between the complexification of this algebra and the standard model of particle physics, its minimal left-right-symmetric $SU(3)\times SU(2)_{L}\times SU(2)_{R}\times U(1)$ extension, and $Spin(10)$ unification. This suggests a geometric interpretation, where a single generation of standard model fermions is described by the tangent space $(\mathbb{C}\otimes\mathbb{O})^{2}$ of the complex octonionic projective plane, and the existence of three generations is related to $SO(8)$ triality.

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

Engagement Intensity as a Learner-Modeling Signal for Adaptive AI Ethics Instruction

arXiv:2606.18548v1 Announce Type: cross Abstract: Adaptive AI ethics instruction in graduate research training benefits from intake measures that reflect differences in prior LLM experience. Prior coursework or workshop attendance is an obvious candidate, but it is not clear whether it is associated with pre-instruction ratings on key AI perception items. We compare three candidate intake features, self-reported usage frequency, self-rated LLM familiarity, and prior AI education, across five baseline perception outcomes in 93 bioscience graduate and postdoctoral trainees enrolled in a required research ethics course. Usage frequency shows Holm-corrected associations with all five outcomes, self-rated familiarity with three, and prior AI education with none. A threshold-like pattern at the lower end of the scale is most visible for training interest and accuracy trust rather than appearing as a uniform gradient across all five outcomes. In a short intake survey, reported LLM use is more consistently associated with these perceptions than prior coursework or workshops, with self-rated familiarity serving as a secondary indicator. These results suggest that simple pre-instruction behavioral signals can inform lightweight intake profiling for adaptive AI ethics education.

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

Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining

arXiv:2601.22108v2 Announce Type: replace-cross Abstract: Continued pretraining is optimized with fixed self-supervised tasks but selected by downstream performance, creating a coarse feedback loop in which practitioners evaluate checkpoints, change data mixtures or objectives, and restart runs, while individual updates remain blind to target capabilities. We ask whether a small set of verifiable downstream examples can provide step-level feedback without directly supervising the learner. We introduce V-pretraining, which decouples a learner trained only with a self-supervised loss from a lightweight task designer that constructs targets or views for unlabeled batches. Given the current learner and batch, V-pretraining scores a candidate construction by predicting the first-order reduction in downstream loss after the induced self-supervised update. The designer maximizes this value; the learner then applies the update with targets or views detached, so downstream labels never update learner parameters. We instantiate V-pretraining as adaptive top-K soft targets for language modeling and learned views or masks for self-supervised vision. Across both modalities, V-pretraining improves target capabilities without degrading generalization. Under wall-clock-matched continued pretraining, it improves GSM8K Pass@1 for Qwen models using 1,024 GSM8K examples only as feedback, including a +7.4 point single-run gain for Qwen2.5-0.5B. In vision, it improves DINOv3 transfer to ADE20K semantic segmentation and NYUv2 depth estimation while preserving ImageNet linear accuracy, suggesting that feedback-guided task construction can improve target capabilities without collapsing general-purpose representations.

07.
bioRxiv (Bioinfo) 2026-06-10

When batch correction corrupts gene expression: uncovering distortions in correlation structures

Batch correction is essential for integrating datasets and enabling population-level insights into health and disease. Embedding-based approaches are among the most widely used solutions, but here we highlight a critical, overlooked limitation: these methods can distort feature-to-feature (e.g., gene gene) relationships, potentially undermining downstream analyses. We investigate this issue and introduce a novel metric to quantify it.

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

PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning

Machine unlearning for large language models (LLMs) aims to remove specified knowledge while preserving the rest of the model's capabilities. However, the boundary between knowledge to forget and knowledge to retain is often unclear, since related and even distant information may be entangled in the model. In this paper, we study LLM unlearning from a data-centric perspective and measure how unlearning effects propagate from the forget set to same-domain and distant-domain knowledge. We find a consistent decay pattern: collateral damage is strongest near the forget set, weakens with semantic distance, but does not disappear at domain boundaries. We further ask whether such damage can be audited before unlearning is executed. We formulate forget-set auditing as a pre-unlearning prediction task and analyze which data features are most predictive of downstream damage. Our results show that interaction features between the forget set and evaluation set provide the strongest signals, suggesting that collateral damage is partly reflected in data geometry before model updates occur. These findings position forget-set auditing as an early warning tool for identifying risky unlearning runs and designing more reliable unlearning procedures.

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

Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks

arXiv:2606.18436v1 Announce Type: cross Abstract: Sparse point observations are increasingly available for precipitation nowcasting, but it is unclear how much they improve dense radar-field forecasts. We partially address this question with a multimodal graph neural network nowcasting system over the Nordic radar domain. The model predicts rain rate every five minutes up to two hours ahead and is trained with different combinations of radar history, MEPS numerical weather prediction, Netatmo surface observations, MSG satellite channels, stochastic noise, and CRPS-based ensemble losses. The study is designed as an ablation of operationally relevant information sources and training objectives. We compare radar-only, NWP-informed, station-informed, satellite-informed, noise-augmented, and CRPS-based configurations using complementary diagnostics on the radar grid, at station locations, for rain onset, and through oracle, displacement, and amplitude scores. The results show that each source improves a different part of the forecast problem. MEPS stabilises radar-only extrapolation, Netatmo observations improve local station and onset diagnostics, and satellite predictors reduce some station-level biases but may activate rain too early when used deterministically. CRPS-based configurations provide the most consistent radar-grid gains, while the combined satellite and CRPS setup gives the best overall oracle/DAS score. These results do not support the conclusion that point observations are uninformative for nowcasting, but they show that local observational skill and spatially coherent radar-field skill are distinct targets. The practical implication is that sparse observations can provide useful local constraints, but their benefit for radar-like fields depends on the training loss, uncertainty representation, and how observation support is encoded in the model.

10.
arXiv (CS.CL) 2026-06-12

NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning

The rapid updates of online news make tracking event developments challenging, highlighting the need for timeline summarization (TLS). Hallucinations, where LLM-generated content deviates from source news, still remain a critical issue in LLM-based TLS and are not well studied in existing works. To bridge this gap, we identify two primary types of hallucinations: unfaithful content during news summarization and information omission in date-event summarization. Then, we propose NTS-CoT, a novel framework that leverages Chain-of-Thought (CoT) reasoning to mitigate hallucinations in TLS. The framework consists of three key modules: i) Element-CoT to capture essential news elements for faithful summarization, ii) Date Selection to combine temporal saliency and event prominence for timestamp selection, and iii) Causal-CoT to infer causal relationships and reduce omissions in date-event summarization. Extensive experiments, including quantitative analysis on three TLS benchmarks and human evaluation, demonstrate that NTS-CoT outperforms state-of-the-art baselines, effectively mitigating hallucinations and improving LLM-based TLS performance. Our source code is available at https://anonymous.4open.science/r/NTS-CoT .

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

Spectral DPPs via NEPv: A Scalable Continuous Relaxation of Determinantal MAP for Diversity-Aware Data Selection

arXiv:2606.19411v1 Announce Type: new Abstract: Selecting a small, diverse, high-quality subset from a massive pool of candidates is a recurring primitive in modern machine learning – data curation and coreset selection for training and fine-tuning large models, active-learning batch acquisition, prompt and exemplar selection for in-context learning, retrieval diversification, and experimental design. Determinantal Point Processes (\operatorname{DPP} s) give a principled, well-calibrated notion of diversity for this task, but their MAP objective – pick a size-$k$ subset $S$ maximizing $\logdet(L_S)$ – is NP-hard, and the standard greedy and sampling algorithms scale superlinearly in the ground-set size $n$. This cost is prohibitive precisely in the data-centric regime where diversity matters most, where $n$ ranges over millions to billions of candidate examples, features, or embeddings. We recast \operatorname{DPP}-MAP as a continuous optimization problem over the Stiefel manifold, and show that its first-order optimality conditions form a Nonlinear Eigenvalue Problem with eigenvector dependency (\operatorname{NEP}v) of a previously unstudied form. This \operatorname{NEP}v\ admits a self-consistent field (\operatorname{SCF}) iteration with a spectral-gap-based local contraction guarantee, giving a principled iterative solver where the diversity objective drives an eigenvector-dependent operator. The resulting algorithm, \OurMethod, requires only matrix-vector products with the kernel and runs in time $O\!\big((ndk+nk^2)\,t\big)$ for a small number of iterations $t$, scaling near-linearly in $n$ and integrating directly with low-rank and feature-map kernels common in ML. This paper focuses on the relaxation, solver, and scaling analysis; full real-data benchmarking is left to a planned empirical study.

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

AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility

arXiv:2606.13608v1 Announce Type: new Abstract: Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate interfaces, one for the benchmark and one for the agent, while AAA only needs one; this yields a generic, unified framework that separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and reproducibility. To evaluate our design at scale, we conduct two studies: a five-month open competition that drew 298 judge agents across 12 categories together with 467 subject agents from independent participants, showing that AAA applies across a heterogeneous range of benchmarks; and a case study on coding agents that confirms agentified evaluation preserves fidelity with the public record while surfacing previously missing head-to-head results, yielding research insights about agent design. Combining a community-scale field study and a controlled coding case study, we verify that AAA delivers coverage, practicality, and fidelity across heterogeneous scenarios at scale. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.

13.
arXiv (CS.AI) 2026-06-12

DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks

arXiv:2606.12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 associated rubrics, capturing widely discussed and timely information demands of real-world users. Each task is decomposed into subtasks and evaluated with cascade rubrics across disentangled dimensions. Through cascade performance attribution and user-centric aggregation, we derive highly interpretable scores for each dimension, along with a user preference score. Our results on 17 agentic systems show that current systems still fall short of users' expectations. To facilitate future research, our dataset and code are made publicly available at https://github.com/AGI-Eval-Official/DailyReport.

14.
arXiv (CS.CL) 2026-06-16

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning

Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, standard GRPO relies on scalar correctness rewards that are often non-injective with respect to semantic content: distinct reasoning paths receive identical rewards. This leads to a Diversity-Quality Inconsistency, where the policy collapses into a narrow set of dominant modes while ignoring equally valid but structurally novel strategies. To bridge this gap, we propose Diversity-aware Reward Adjustment (DRA), a theoretically grounded framework that calibrates the reward signal using the semantic density of sampled groups. By leveraging Submodular Mutual Information (SMI), DRA implements an Inverse Propensity Scoring (IPS) mechanism that effectively de-biases the gradient estimation. This creates a repulsive force against redundancy, driving the policy to achieve better coverage of the high-reward landscape. Our method is plug-and-play and integrates seamlessly with GRPO variants. Empirical evaluations on five math benchmarks demonstrate that DRA-GRPO consistently outperforms strong baselines, achieving an average accuracy of 58.2% on DeepSeek-R1-Distill-Qwen-1.5B with only 7,000 training samples and $55 cost, highlighting the critical role of diversity calibration in data-efficient alignment. The code is available at https://github.com/xiwenc1/DRA-GRPO.

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

Single vs. Multiple Branches in DeepONet and S-DeepONet: Network Architecture Follows Coupling in Multiphysics Systems

arXiv:2507.03660v2 Announce Type: replace Abstract: `Real-time prediction of complex physical systems requires surrogate models that learn from data while representing strong multiphysics coupling. Deep Operator Networks have shown success in single-physics problems, yet their effectiveness in capturing nonlinear interactions in coupled systems (such as thermo-mechanical or electro-thermal coupling) remains underexplored. Here we pose a practical question: should the architecture of a neural operator reflect the strength of physical coupling it aims to model? We compare single-branch and multi-branch designs, in both feedforward and sequential recurrent forms, across three representative systems: a reaction–diffusion problem with heterogeneous sources, a nonlinear thermo-electrical problem with temperature-dependent conductivity and Joule heating, and a viscoplastic thermo-mechanical model of steel solidification. Single-branch networks consistently outperform multi-branch variants in tightly coupled regimes by encouraging shared latent representations, whereas multi-branch designs remain favorable for decoupled or single-physics tasks. Once trained, these surrogates deliver full-field predictions up to $1.8 \times 10^4$ times faster than physics-based solvers.

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

Honeypot Protocol

作者:

arXiv:2604.13301v1 Announce Type: cross Abstract: Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different perceived conditions. We introduce the honeypot protocol, which tests for context-dependent behavior by varying only the system prompt across three conditions (evaluation, synthetic deployment, explicit no-monitoring) while holding the task, environment, and scoring identical. We evaluate Claude Opus 4.6 in BashArena across all three conditions in both honest and attack modes. The model achieved 100% main task success and triggered zero side tasks uniformly across conditions, providing a baseline for future comparisons with stronger attack policies and additional models.

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

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relevant facts, identifiers, constraints, and conditions observed through user interaction and tool calls. In standard agents, task states are not represented separately. Observations, tool returns, and policy instructions are placed in the prompt, leaving agents to reconstruct the relevant states from the prompt each time they decide what to do next. This design makes state management implicit, creating two common failure modes. An agent may retrieve the right facts but later ground its decision in stale, missing, or incorrect information; and a syntactically valid tool call may still violate a domain policy that depends on the current task state. We introduce \textsc{LedgerAgent}, an inference-time method for tool-calling agents that maintains observed task states in a separate ledger and renders the states into the prompt. The ledger is also used to check state-dependent policy constraints before environment-changing tool calls are executed, blocking policy violations. Across four customer-service domains and a mixed panel of open- and closed-weight models, \textsc{LedgerAgent} improves average pass\textasciicircum{}k over a standard prompt-based tool-calling approach, with the largest gains under stricter multi-trial consistency metrics.

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

HoloRec: Holistic Encoding and Interleaved Reasoning for Generative Recommendation

arXiv:2606.15331v1 Announce Type: cross Abstract: Generative recommendation models that formulate the task as sequence generation overcome the objective fragmentation problem of traditional cascade architectures, yet existing approaches still suffer from flat semantic representations lacking hierarchical structure for multi-step reasoning and an externally constructed chain-of-thought (CoT) that requires expensive annotations and remains disconnected from the generation objective. We propose HoloRec, an endogenous chain-of-thought recommendation mechanism that unifies representation, reasoning, and generation by constructing a hierarchical semantic encoding matrix via multi-granularity nested residual quantization optimized by a holistic reconstruction loss. HoloRec supports two inference modes: a non-thinking mode that uses lightweight multi-granularity supervised alignment for fast prediction, and a thinking mode that employs an interleaved reasoning scheme to generate CoT steps on the fly, directly embedding reasoning into the generation process without external data. Experiments on multiple public recommendation datasets demonstrate that HoloRec consistently outperforms baselines, with especially significant gains in sparse scenarios, and the thinking mode achieves better accuracy than the non-thinking mode with only modest inference overhead.

19.
arXiv (CS.AI) 2026-06-15

YeasierAgent: Agentic Social Sandbox as a Canvas for Intent-Driven Creation of Platform-Agnostic Symbiotic Agent-Native Applications

作者:

arXiv:2606.13722v1 Announce Type: new Abstract: This paper introduces YeasierAgent, an application-building paradigm based on symbiotic agents, narrative worlds, and scene-aware interaction. It challenges the conventional device-coupled model of software by redefining applications as collaborative spaces among users, agents, and worlds. We present a system architecture that achieves two primary contributions: (1) enabling the rapid, cross-platform construction of agent-native applications by utilizing platform-agnostic interactive units (agents, scenes, dialogue) rather than fixed graphical layouts; and (2) unifying the emotional companionship and practical tool execution attributes of intelligent agents within a single experiential sandbox. By integrating automated generation, user-created worlds, and spatial multi-agent collaboration, YeasierAgent formalizes the category of Symbiotic Agent-Native Applications, demonstrating a shift from isolated, tool-specific chatbots toward cohesive, socially embedded computational environments.

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

Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds

arXiv:2606.19941v1 Announce Type: new Abstract: Compositionality is believed to be the foundation for generalization, enabling models to reuse meaningful primitives in novel combinations. Yet, models trained with standard gradient-based optimization rarely, and often only weakly, exhibit compositional internal structure, and it remains unclear how or why such compositionality forms. In this work, we show that compositionality emerges in a narrow connectivity-depth sweet spot. Along the connectivity axis, compositionality only appears in some specifically sparse networks, heavily depends on which connections remain rather than on weights' sparsity alone. Along the depth axis, compositionality emerges within a narrow, target-dependent regime, peaking at specific depths, while both shallower and deeper networks fail. When either the depth or connectivity condition is violated, gradient descent silently converges to fractured solutions rather than compositional ones. To discover and exploit this emergence, we introduce (i) similarity-based pruning (SP) to recover compositional connectivity and (ii) a heuristic depth predictor to estimate where compositionality is most likely to appear. Finally, we support these empirical findings with a theoretical framework based on compositional sparsity, volume-ratio arguments, and feature-interference bounds, explaining why compositional solutions are reachable only in a narrow depth-connectivity regime.

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

Towards Functional Correctness of Large Code Models with Selective Generation

arXiv:2505.13553v3 Announce Type: replace-cross Abstract: The hallucination of code generation models hinders their applicability to systems requiring higher safety standards. One critical bottleneck in addressing code hallucination is the difficulty of identifying the functional correctness of generated code, due to its unnatural form. We address this core bottleneck by automatically generating unit tests using dynamic code analysis tools, leveraging the executable nature of code. Accordingly, we propose a selective code generator that abstains from uncertain generations – based on the functional correctness evaluated by generated unit tests – to theoretically control the correctness among non-abstained answers, \ie the false discovery rate. Finally, we propose to use generated unit tests in evaluation as well as in learning for precise code evaluation, calling this paradigm FuzzEval. We demonstrate the efficacy of our method along with the controllability of code hallucination and reasonable selection efficiency.

22.
arXiv (CS.CV) 2026-06-12

Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension

Visual Text Comprehension (VTC) renders text into images for a vision-language model (VLM) to read, sidestepping LLM context-window limits and powering applications from long-page OCR to multi-page memory QA. Yet existing VTC pipelines treat rendering and layout as a fixed, content-agnostic preprocessing step and offer little mechanistic understanding of how VLMs internally process visualized text. Through a focused empirical study on VTC QA tasks, we reveal that VLMs exhibit a localization-without-utilization regime: evidence-localizing attention emerges sharply in the middle-to-late layers and is largely decoupled from answer correctness, yet simply enlarging the localized spans on the rendered page recovers a large fraction of the failures. Building on these observations, we propose AGAR (Attention-Guided Adaptive Rendering), a training-free, model-agnostic method that leverages a VLM's own middle-to-late layer attention to identify the top-K important visual patches, maps them back to word spans, and re-renders the page with those spans enlarged before re-inferring the answer. Extensive experiments across nine VTC benchmarks (short-form, long-context, and multi-page memory QA) and four VLM backbones show that AGAR (i)consistently improves off-the-shelf VLMs as a plug-and-play enhancement, (ii)composes with VLM post-training to yield further gains, and (iii)remains robust under both visual- and text-side input degradation.

23.
arXiv (CS.AI) 2026-06-16

RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments

arXiv:2606.15862v1 Announce Type: new Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation. RetailBench models retail management as a partially observable decision process and is designed to support thousand-day-scale simulations. In this environment, agents must manage pricing, replenishment, supplier selection, shelf assortment, inventory aging, customer feedback, external events, and cash-flow constraints. We evaluate seven contemporary LLMs under representative agent frameworks over a 180-day evaluation horizon and compare them with a privileged oracle policy. Results show substantial variation across models: only a small subset survives the full evaluation horizon, and even the strongest LLM runs remain substantially behind the oracle policy in final net worth and sales outcomes. Behavioral analysis attributes these gaps to incomplete evidence acquisition, surface-level decision making, and the lack of a consistent long-horizon policy. RetailBench provides a controlled testbed for studying reliable autonomy in economically grounded long-horizon decision-making.

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

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention

arXiv:2510.04212v4 Announce Type: replace-cross Abstract: The pursuit of computational efficiency has driven the adoption of low-precision formats for training transformer models. However, this progress is often hindered by notorious training instabilities. This paper provides the first mechanistic explanation for a long-standing and unresolved failure case where training with flash attention in low-precision settings leads to catastrophic loss explosion. Our in-depth analysis reveals that the failure is not a random artifact but caused by two intertwined phenomena: the emergence of similar low-rank representations within the attention mechanism and the compounding effect of biased rounding errors inherent in low-precision arithmetic. We demonstrate how these factors create a vicious cycle of error accumulation that corrupts weight updates, ultimately derailing the training dynamics. To validate our findings, we introduce a minimal modification to the flash attention that mitigates the bias in rounding errors. This simple change stabilizes the training process, confirming our analysis and offering a practical solution to this persistent problem. Code is available at https://github.com/ucker/why-low-precision-training-fails.

25.
arXiv (math.PR) 2026-06-11

Markov property and path regularity for the solutions to SPDEs driven by cylindrical-martingale valued measures

arXiv:2606.12381v1 Announce Type: new Abstract: In this paper we prove the Markov property for the solution to stochastic partial differential equations driven by a cylindrical orthogonal martingale-valued measure. We assume our coefficients are time-dependent and satisfy some growth and Lipschitz conditions. We also prove that for time-independent coefficients and under mild assumptions on the cylindrical orthogonal martingale-valued measure, the solutions to our stochastic partial differential equations are Feller. Finally, in the case that the $C_{0}$-semigroup is quasi-contraction, we show that the solution to our stochastic partial differential equation possesses a càdlàg version.