中 EN
登录 注册账户

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。

登录 注册账户
01.
arXiv (CS.AI) 2026-06-18

TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology

作者:
Hannah Le↗Ramesh Ramasamy↗Alex Urrutia↗Mahsa Yazdani↗Tim Proctor↗Kenny Workman↗

arXiv:2606.19245v1 Announce Type: new Abstract: Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions. We introduce TherapeuticsBench Preclinical Pharmacology (TxBench-PP), a verifiable benchmark for small-molecule preclinical pharmacology and the first focused slice of a broader TherapeuticsBench effort across drug-discovery stages and therapeutic modalities. TxBench-PP tests whether agents can recover accurate conclusions from real-world assay data rather than memorized facts from literature. The benchmark contains 100 evaluations indexed by program stage, assay type, and task structure, spanning mechanism-of-action (MoA) and pharmacodynamic (PD) reasoning, compound-target engagement, causal target validation, developability and safety, and translational efficacy. Agents receive realistic workflow snapshots, inspect files in a coding environment, and return structured answers graded deterministically. Across 16 model-harness configurations, comprising 11 models and 4,800 trajectories, no system reliably recovered preclinical pharmacology decisions. The strongest configuration, Claude Opus 4.8 / Pi, passed 59.3\% of endpoint attempts (178/300; 95\% CI, 51.1-67.6), followed by GPT-5.5 / Pi at 55.3\% (166/300; 47.0-63.6).

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-16

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

作者:
Jiahao Huo↗Wenjie Qu↗Yibo Yan↗Kening Zheng↗Jiaheng Zhang↗Xuming Hu↗Philip S. Yu↗Mingxun Zhou↗

Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remains difficult because such attacks globally disrupt watermark signals by changing sentence order. In this work, we propose SAMark, a self-anchored watermarking framework that removes the dependency on sentence order by establishing a step-independent green region in semantic space. To improve detectability, we introduce a multi-channel hyperbolic scoring mechanism that amplifies watermark signals while suppressing noise from weakly aligned candidates. We further propose a diversity-aware filtering strategy that combines hard filtering with soft regularization, extending beyond simple n-gram repetition filters to address semantic redundancy. Experimental results show that SAMark achieves up to 90.2% TP@FP1% under typical paragraph-level paraphrasing attacks, outperforming the strongest prior baseline by more than 30% on average, while maintaining generation quality competitive with unwatermarked text and breaking the robustness-quality trade-off that limits prior methods.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CV) 2026-06-18

S3OD: Towards Generalizable Salient Object Detection with Synthetic Data

作者:
Orest Kupyn↗Hirokatsu Kataoka↗Christian Rupprecht↗

Salient object detection exemplifies data-bounded tasks where expensive pixel-precise annotations force separate model training for related subtasks like DIS and HR-SOD. We present a method that dramatically improves generalization through large-scale synthetic data generation and ambiguity-aware architecture. We introduce S3OD, a dataset of over 139,000 high-resolution images created through our multi-modal diffusion pipeline that extracts labels from diffusion and DINO-v3 features. The iterative generation framework prioritizes challenging categories based on model performance. We propose a streamlined multi-mask decoder that handles the inherent ambiguity in salient object detection by predicting multiple valid interpretations. Models trained only on synthetic data achieve 20-50% error reduction in cross-dataset generalization, while fine-tuned versions reach state-of-the-art performance across DIS and HR-SOD benchmarks.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-16

Neuron Level Analysis of Large Language Model in Legal Domain Reasoning

作者:
Eri Onami↗Youmi Ma↗Shuhei Kurita↗Naoaki Okazaki↗

We presented a neuron-level analysis of legal-domain reasoning in LLMs, comparing it with other applied domain tasks across seven open-weight models. Using neuron attribution scores to rank and suppress influential neurons, we confirmed that suppressing the identified neurons collapses accuracy on the target task, whereas suppressing the same number of random neurons does not. We further found a small subset of neurons influential across all seven tasks; once these are removed, suppressing the remaining neurons degrades only the task they were identified from, revealing genuinely task-specific neurons in every model studied. Within the legal domain, the three benchmarks exhibit relatively high neuron overlap and tend to be affected jointly, suggesting of legal components neurons that span jurisdictions. The distribution of identified neurons in our experiments suggests that the hypothesis that influential neurons are concentrated in middle MLP layers may depend on the input format and content, rather than being a universal phenomenon.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-11

Characterizing Software Aging in GPU-Based LLM Serving Systems

作者:
Domenico Cotroneo↗Bojan Cukic↗

arXiv:2606.11916v1 Announce Type: cross Abstract: This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems. Traditional aging studies focus on CPU-centric software with relatively regular workloads; LLM serving is different, spanning a Python host and a CUDA device, handling requests whose cost varies by orders of magnitude, and relying on rapidly evolving software stacks. We run a 216-hour campaign across six co-located deployments under identical stress conditions, monitor host, device, and client metrics in parallel, and apply a statistical pipeline that accounts for autocorrelation and multiple testing. Our results reveal statistically significant memory aging in all deployments, with leak rates strongly dependent on the serving runtime and deployment configuration. Beyond these findings, we provide a reproducible framework that opens a research direction at the intersection of the software aging and rejuvenation and LLM serving communities.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.LG) 2026-06-15

Arbitrary control over multimode wave propagation for machine learning

作者:
Tatsuhiro Onodera↗Martin M. Stein↗Benjamin A. Ash↗Mandar M. Sohoni↗Melissa Bosch↗Ryotatsu Yanagimoto↗Marc Jankowski↗Timothy P. McKenna↗Tianyu Wang↗Gennady Shvets↗Maxim R. Shcherbakov↗Logan G. Wright↗…

arXiv:2402.17750v2 Announce Type: replace-cross Abstract: Controlled multimode wave propagation can enable more space-efficient photonic processors than architectures based on discrete components connected by single-mode waveguides. Instead of defining discrete elements, one can sculpt the continuous substrate of a photonic processor to perform computations through multimode interference in two dimensions. Here we designed and demonstrated a device with a refractive index that can be rapidly reprogrammed across space, allowing arbitrary control of wave propagation. The device, a two-dimensional programmable waveguide, uses parallel electro-optic modulation of the refractive index of a slab waveguide with about $10^4$ programmable spatial degrees of freedom. We implemented neural network inference on benchmark tasks with up to $49$-dimensional vectors in a single pass, without digital pre-processing or post-processing. Theoretical and numerical analyses further indicated that two-dimensional programmable waveguides may offer not only a constant-factor reduction in device area but also a scaling benefit, with the area required growing as $N^{1.5}$ rather than $N^2$.

阅读与讨论 → 访问原文 →
07.
arXiv (quant-ph) 2026-06-17

Cumulant expansion approach to the decay dynamics of interacting Mössbauer nuclei after strong impulsive excitation

作者:
Miriam Gerharz↗J\"org Evers↗

arXiv:2510.00970v2 Announce Type: replace Abstract: Recent progress in accelerator-based x-ray sources brings higher excitation of ensembles of Mössbauer nuclei closer to experimental feasibility. Yet, a theoretical modeling of the decay dynamics of the interacting nuclear ensemble after the impulsive excitation is still an open challenge. Here, we derive a set of nonlinear equations which is capable of efficiently modeling large nuclear ensembles for arbitrary degrees of excitation. As key signature for higher excitation, we identify a non-linear time-evolution of the nuclear dipole phase, which can be tuned via the scattering geometry, and interferometrically be measured. Furthermore, we identify interesting finite-size effects in the nuclear dynamics of small ensembles. Our results provide important guidance for future experiments aiming at the non-linear excitation of nuclei. We further envision the exploration of finite size-effects in Mössbauer spectroscopy with highest spatial resolution, i.e., small sample volumes.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-16

Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension

作者:
Michael Crawshaw↗Mingrui Liu↗

arXiv:2602.12471v2 Announce Type: replace Abstract: We consider the optimization problem of minimizing the logistic loss with gradient descent to train a linear model for binary classification with separable data. With a budget of $T$ iterations, it was recently shown that an accelerated $1/T^2$ rate is possible by choosing a large stepsize $\eta = \Theta(\gamma^2 T)$ (where $\gamma$ is the dataset's margin) despite the resulting non-monotonicity of the loss. In this paper, we provide a tighter analysis of gradient descent for this problem when the data is two-dimensional: we show that GD with a sufficiently large learning rate $\eta$ finds a point with loss smaller than $\mathcal{O}(1/(\eta \gamma^2 T))$, as long as $T \geq \Omega(n/\gamma + 1/\gamma^2)$, where $n$ is the dataset size. Our improved rate comes from a tighter bound on the time $\tau$ that it takes for GD to transition from unstable (non-monotonic loss) to stable (monotonic loss), via a fine-grained analysis of the oscillatory dynamics of GD in the subspace orthogonal to the max-margin classifier. We also provide a lower bound of $\tau$ matching our upper bound up to logarithmic factors, showing that our analysis is tight.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.LG) 2026-06-19

FloatDoor: Platform-Triggered Backdoors in LLMs

作者:
Nils Loose↗Jonas Sander↗Felix M\"achtle↗Thomas Eisenbarth↗

arXiv:2606.19535v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts. Recent work has shown that an identical model can produce measurably different outputs depending on the deployment platform, a consequence of non-associative floating-point arithmetic and divergent kernel implementations. We study the security implications of this platform-dependent variability and uncover a novel attack surface on LLM deployments. We introduce FloatDoor, the first input-independent, platform-triggered backdoor attack against generative LLMs. The compromised model exhibits adversary-chosen behavior when served on a target platform and is otherwise benign. FloatDoor is realized through two lightweight LoRA adapters, one that amplifies inter-platform numerical divergence and one that binds the resulting platform signature to a malicious downstream task, while leaving aggregate model utility largely intact. FloatDoor exploits a pronounced time-of-check, time-of-use gap between model auditing and serving. We demonstrate FloatDoor on Qwen3-4B across a broad range of deployment targets, including NVIDIA GPUs, Google TPUs, AWS Graviton, and Alibaba Yitian-710. As a final case study, we show that FloatDoor reliably induces exploitable code vulnerabilities on a chosen target platform. Our results establish a new class of attacks on LLM deployments and underscore the pressing need for trusted model supply chains in sensitive, LLM-powered applications.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CV) 2026-06-17

Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor

作者:
Andrea Mattia Garavagno↗Daniele Leonardis↗Antonio Frisoli↗

The current trend of applying transfer learning from convolutional neural networks (CNNs) trained on large datasets can be an overkill when the target application is a custom and delimited problem, with enough data to train a network from scratch. On the other hand, the training of custom and lighter CNNs requires expertise, in the from-scratch case, and or high-end resources, as in the case of hardware-aware neural architecture search (HW NAS), limiting access to the technology by non-habitual NN developers. For this reason, we present ColabNAS, an affordable HW NAS technique for producing lightweight task-specific CNNs. Its novel derivative-free search strategy, inspired by Occam's razor, allows to obtain state-of-the-art results on the Visual Wake Word dataset, a standard TinyML benchmark, in just 3.1 GPU hours using free online GPU services such as Google Colaboratory and Kaggle Kernel.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CV) 2026-06-15

HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities

作者:
Yijun Liu↗Jie Huang↗Zeyue Xue↗Yuming Li↗Ruizhe He↗Haoran Li↗Shijia Ge↗Siming Fu↗

Reward models guide text-to-image (T2I) systems toward outputs aligned with human preferences. However, typical reward models such as HPSv3 are trained on pre-annotated data from earlier T2I models, without accounting for quality discriminative shifts arising from evolving model capabilities and reinforcement learning (RL) iterations, limiting their broader applicability. In this work, we propose HPSv3++, a reward model framework that elevates the HPSv3 model for varying T2I model capabilities and their RL iteration changes across the full capability-iteration spectrum. Specifically, we first introduce HPDv3++, a 212K dual-dimension preference dataset annotated for text fidelity and aesthetic quality using a recent high-capability (Qwen-Image) model with human supervision. We then propose a two-stage training framework. Stage 1 employs data-aware orthogonal gradient projection to incorporate diverse aesthetic perception from HPDv3++ while preserving the original effective human preference knowledge in HPSv3. Stage 2 further leverages unlabeled data from T2I models spanning different capability levels and RL iterations, and introduces a joint capability-iterations conditioned signal for the reward model together with a standard deviation-driven unsupervised guidance mechanism, strengthening reward model across the capability-iteration spectrum. HPSv3++ achieves state-of-the-art preference prediction, outperforming HPSv3 9.8% on HPDv3, 5.5% on GenAI-Bench, while achieving 79.1%/88.1% on our proposed HPDv3++. When used for T2I RL training, it consistently improves GenEval scores across diverse T2I models, demonstrating its wide-range capabilities. The code is available at https://github.com/PlantPotatoOnMoon/HPSv3-PlusPlus.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CL) 2026-06-12

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

作者:
Baochang Ren↗Xinjie Liu↗Xi Chen↗Yanshuo Liu↗Chenxi Li↗Daqi Gao↗Zeqin Su↗Jintao Xing↗Zirui Xue↗Rui Li↗Xiangyu Zhao↗Shuofei Qiao↗…

Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan protocols, yet the execution of those protocols at the bench still requires a human operator. Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution, but existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent liquids, or fixed protocol workflows found in scientific laboratories. Closing this gap requires both laboratory-specific supervision and a unified learning framework that can accommodate the diverse robot embodiments used to execute experimental protocols. We therefore identify data and embodiment as central bottlenecks alongside model design. To address the data side, we build RoboGenesis, a simulation-based workflow and data engine that composes configured laboratory workflows from atomic skills, validates and filters rollouts, and exports structured demonstrations across supported robot profiles. On the policy side, we present LabVLA, trained with a two-stage recipe: FAST action token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation. On the LabUtopia benchmark, LabVLA achieves the highest average success rate among all evaluated baselines under both in-distribution and out-of-distribution settings.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CV) 2026-06-17

ED3R: Energy-Aware Distributed Disaster Detection Enabled by Cooperative Robotic Agents

作者:
Lina Magoula↗Nikolaos Koursioumpas↗Nancy Alonistioti↗Ramin Khalili↗

Robotics are expected to support environmental monitoring and natural disaster management, where decisions must be made under uncertainty, resource limitations, and strict operational constraints. In critical missions, such as wildfires, robotic agents must not only identify hazardous events with sufficient confidence, but also manage the energy cost and time until detection. This paper introduces ED3R, an energy-aware distributed framework for wildfire detection under uncertainty. ED3R enables hierarchical cooperative decision-making between a robot and a remote controller. The remote controller decides upon the robot's motion, while the robot senses the environment and decides where to execute the wildfire detection (onboard or remotely) and how. The common goal is to detect wildfires with a required confidence while minimizing the energy consumed by any robot operation. ED3R further integrates mechanisms to avoid nearby obstacles, prevent redundant exploration, enable adaptive early mission completion, and ensure feasibility through a custom penalty function. ED3R also introduces a forward-looking capability, enabled through distributed neural regression models that allow the agents to anticipate the future by evaluating candidate strategies before execution. The framework is evaluated through realistic robotics simulations, ablation studies, and baseline comparisons. Overall, ED3R achieves a mission success rate of up to 97.18%. Especially in the most demanding missions, it reduces energy consumption by up to 36.4% and detects wildfires up to 41% faster than baselines.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.LG) 2026-06-19

Optimal Deterministic Multicalibration and Omniprediction

作者:
Georgy Noarov↗Aaron Roth↗

arXiv:2606.20557v1 Announce Type: new Abstract: A model is multicalibrated on a collection of group weights $G$ if it is calibrated – i.e. unbiased even conditional on its prediction – not just overall, but also after reweighting contexts by each $g \in G$. It is a useful property for many downstream applications and is a basic desideratum of trustworthy machine learning. Before this work, all predictors known to attain the minimax-optimal $\widetilde O(\varepsilon^{-3})$ sample complexity rate for $\varepsilon$-multicalibration were randomized, while deterministic predictors were known only with substantially worse sample complexity. Whether randomization is necessary for optimal sample complexity in multicalibration was explicitly asked by [CLNR26] and implicitly in several prior works. We resolve this open problem by giving a minimax-optimal multicalibration algorithm that outputs a deterministic predictor. We then generalize the algorithm to produce optimal deterministic predictors that satisfy outcome indistinguishability (OI) with respect to finite or finitely covered collections of tests. As an application, this also gives deterministic omnipredictors and panpredictors with optimal sample complexity, resolving open problems posed by [OKK25] and [BHHLZ25].

阅读与讨论 → 访问原文 →
16.
arXiv (CS.CL) 2026-06-11

LLMpedia: A Transparent Framework to Materialize an LLM's Encyclopedic Knowledge at Scale

作者:
Muhammed Saeed↗Simon Razniewski↗

Benchmarks like MMLU suggest flagship language models approach factuality saturation above 90\%. LLMpedia shows this picture is incomplete. We materialize ${\sim}$1.3M encyclopedia articles entirely from parametric memory across three model families, then audit every claim against Wikipedia and curated web evidence. For \texttt{gpt-5-mini}, the verifiable true rate is 68.4\% on Wikipedia-covered subjects - more than 21\,pp below MMLU - and the gap is driven by unverifiability (30.5\%), not refutation (1.2\%). Beyond Wikipedia, frontier articles audited against curated web evidence reach 57.6\%; Wikipedia covers only 56.7\% of model-surfaced subjects, and three model families overlap in just 7.3\% of subject choices. In a retrieval-trap benchmark inspired by prior analysis of Grokipedia, LLMpedia is more factual at roughly half the textual similarity to Wikipedia. Every prompt, article, and verdict is released. Data, code, interface: https://llmpedia.net.

阅读与讨论 → 访问原文 →
17.
medRxiv (Medicine) 2026-06-15

Investigation of Intra-Fraction Stability and Inter-Fraction Reproducibility of Deep Inspiration Breath-Hold Across Two Hypofractionated Radiotherapy Regimens in the HYPORT Adjuvant Study.

作者:
MAHATA↗Roy↗Khatua↗Maity↗Barik↗Chakraborty↗Chatterjee↗

Background: Deep Inspiration Breath Hold (DIBH) is a widely used respiratory motion management technique for minimizing cardiac dose in left-sided breast radiotherapy. In the Breast HYPORT Adjuvant study, DIBH was employed for cardiac sparing in patients without nodal irradiation using a standardized institutional protocol with the Varian Real-time Position Management (RPM) system. Both moderate-hypofractionation (control arm - 40Gy in 15 fractions) and one-week hypofractionation (experimental arm - 26 Gy in 5 fractions) regimens were delivered using this protocol. This study aimed to evaluate the robustness of DIBH by analyzing intra-fraction stability and inter-fraction reproducibility of breath-hold amplitude across the two treatment regimens. Methods: Respiratory waveforms acquired during each treatment session were analyzed to determine the median breath-hold amplitude and its standard deviation during beam delivery. Intra-fraction stability was assessed from vari- ations within individual treatment sessions, while inter-fraction reproducibility was evaluated relative to the simula- tion waveform amplitude across all treatment sessions. These parameters were compared between the two HYPORT regimens to examine breath-hold consistency during treatment delivery. Moreover, an additional comparison was made between the one-week hypofractionation regimen and the first five fractions of the moderate-hypofractionation regimen to evaluate the effect of treatment duration . Lung volumes from free-breathing and DIBH CT scans were analyzed to assess the effectiveness of patient breath-hold training. Results: Both arms demonstrated an average 1.7-fold increase of air volume in lung during the breath-hold position, confirming the effective implementation of DIBH during treatment planning and delivery. Structured training resulted in increased breath-hold amplitudes, with gains of 22.87% and 24.16% with respect to the first trial session in the experimental and control arms, respectively. Both regimens receive equivalent doses for approximately the same air volume in lung . Despite the different prescription doses in the two arms (26 Gy vs. 40 Gy), the experimental arm achieved an equivalent mean heart dose of 2.91% (75.6 cGy) compared with 2.95% (118.51 cGy) in the control arm, suggesting a similar cardiac preservation protocol adopted during treatment planning. Intra-fraction stability was similar between the control arm and the experimental arm, with median amplitude variations of 1.006 mm (95% CI: [0.998-1.015]) and 1.079 mm (95% CI: [1.067-1.097]), respectively. In contrast, inter-fraction reproducibility improved in the experimental arm, with lower deviation from simulation amplitude (0.44 {+/-} 0.24 mm vs. 0.66 {+/-} 0.25 mm) for the entire treatment schedule. The stability and reproducibility of experimental arm were further compared with the first five fractions of the control arm. The results were similar to those of the experimental arm. Conclusion: In this study, we compared two treatment regimens in terms of intra-fraction stability and inter-fraction reproducibility during DIBH radiotherapy. Both regimens demonstrated comparable intra-fraction stability, indicating effective motion management irrespective of treatment duration. However, the experimental arm showed better inter- fraction reproducibility, suggesting more consistent breath-hold performance throughout the treatment course. Based on stability and reproducibility, a reasonable narrowing of the DIBH gating window may be implemented with minor changes to the institutional protocol. The observed trend highlights the potential for improved consistency with the experimental approach and supports further investigation to better understand the underlying factors and strengthen these findings in future studies.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.AI) 2026-06-19

Measuring Biological Capabilities and Risks of AI Agents

作者:
Patricia Paskov↗Jeffrey Lee↗Kyle Brady↗Alyssa Worland↗

arXiv:2606.19899v1 Announce Type: cross Abstract: This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks. As these systems enter real research workflows, decision-makers increasingly face evaluation results whose meaning depends on underlying design choices that are often implicit or under-documented. We synthesize current evidence on AI-enabled biological risks and introduce biological agentic evaluations as a promising, but interpretation-sensitive, tool for assessing these systems. Our central contribution is a set of practical, experience-grounded considerations – drawing from our own evaluations – that show how choices around defining, designing, running, scoring, and documenting evaluations materially shape what results do and do not imply about risk. The analysis is intended to help policymakers interpret biological evaluation outputs with appropriate caution; guide public and private funders toward high-leverage investments in AI-biology evaluation research; and support biosecurity practitioners assessing emerging AI systems. A secondary audience includes researchers designing or conducting agentic evaluations within frontier AI labs, AI providers, scientific institutions, and third-party evaluation organizations.

阅读与讨论 → 访问原文 →
19.
bioRxiv (Bioinfo) 2026-06-16

FlowBench: separating planning, fault recovery and interpretation in agentic bioinformatics

作者:
Kurjan↗Cribbs↗A. P↗

Agentic large language model (LLM) systems are being deployed in bioinformatics faster than they are understood, and single-metric evaluations conflate capabilities that fail independently. We introduce FlowBench, a benchmark that decomposes agentic bioinformatics performance into planning, fault recovery, biological interpretation, and end-to-end output-fidelity. Existing systems achieve high plan completeness, but their closed, single-provider designs prevent attribution of performance to scaffolding versus the underlying model. We therefore built FlowAgent, a modular, provider-agnostic framework whose components can be selectively disabled and whose backbone model can be swapped across providers on a shared harness, and used it to evaluate 23 models from three main providers. Three findings emerge. First, generating a valid workflow plan from a named toolchain is largely solved, whereas inferring an appropriate toolchain from biological intent alone is uniformly difficult regardless of model tier, compressing all models into a narrow 44-57% pass-rate band. Second, ablation shows that the dependency-structured plan and a completeness-reflection step drive performance, while adding a same-context validator-driven retry makes structural quality worse. Third, fault recovery and data-grounded interpretation remain unsolved. Models frequently propose fixes that force a clean exit while leaving the underlying data invalid, and data-grounded interpretation lags internal-knowledge recall by a consistent margin. Safety does not emerge from capability, and reasoning-tier models were among the least reliable at recognising unrecoverable faults. Once planning saturates, agent architecture and refusal calibration, not model scale, are the productive frontier.

阅读与讨论 → 访问原文 →
20.
arXiv (quant-ph) 2026-06-16

High-performance gates on trapped ion qubits using counterpropagating pulse-shaped laser beams

作者:
Evangelos Piliouras↗Hisham Amer↗Susan M. Clark↗Melissa C. Revelle↗Edward C. Tortorici↗Matthew N. H. Chow↗Brandon Ruzic↗Daniel S. Lobser↗Brian K. McFarland↗Christopher G. Yale↗Edwin Barnes↗Sophia E. Economou↗…

arXiv:2606.15672v1 Announce Type: new Abstract: Highly-localized light-matter interactions are necessary for scaling trapped-ion architectures. In hyperfine qubits, counterpropagating beams generate entangling gates by coupling with motion, but this effect is undesirable during single-qubit operations. For that reason, single-qubit gates are traditionally implemented with copropagating beams, and the coexistence of two beam geometries adds hardware and computational overhead. In an effort towards collective performance improvement with minimal overhead, we design and implement pulse-amplitude and dephasing robust dynamically corrected gates using Space Curve Quantum Control (SCQC) and compare them against the constant-amplitude gate implementation. We perform gate set tomography on a four-qubit trapped-ion register, and we discover more than 50% error reduction when robust pulses are used. We find that counterpropagating robust gates often outperform their copropagating counterparts and reach error rates as low as $(3.59 \pm 1.25)\cdot 10^{-3}$, using diamond distance as a metric. This value establishes a laser-driven-gate error reference and is merely an order of magnitude higher than the best reported $microwave$ gate on a $single$ ion. Additional experiments reveal that robust pulses can effectively suppress non-Markovian errors that grow during runtime. Our work challenges the widely accepted belief that copropagating gates should be preferred for their weak motional coupling and invites the adoption of high-performance robust pulses that suppress multiple noise sources of the trapped-ion error budget.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-16

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

作者:
Linghua Zhang↗Jun Wang↗Jingtong Wu↗Zhisong Zhang↗

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.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CV) 2026-06-16

When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs

作者:
Beidi Zhao↗Wenlong Deng↗Xinting Liao↗Yushu Li↗Nazim Shaikh↗Yao Nie↗Xiaoxiao Li↗

While Retrieval-Augmented Generation (RAG) is one of the dominant paradigms for enhancing Large Vision-Language Models (LVLMs) on knowledge-based VQA tasks, recent work attributes RAG failures to insufficient attention towards the retrieved context, proposing to reduce the attention allocated to image tokens. In this work, we identify a distinct failure mode that previous study overlooked: Attention Distraction (AD). When the retrieved context is sufficient (highly relevant or including the correct answer), the retrieved text suppresses the visual attention globally, and the attention on image tokens shifts away from question-relevant regions. This leads to failures on questions the model could originally answer correctly without the retrieved text. To mitigate this issue, we propose MAD-RAG, a training-free intervention that decouples visual grounding from context integration through a dual-question formulation, combined with attention mixing to preserve image-conditioned evidence. Extensive experiments on OK-VQA, E-VQA, and InfoSeek demonstrate that MAD-RAG consistently outperforms existing baselines across different model families, yielding absolute gains of up to 4.76%, 9.20%, and 6.18% over the vanilla RAG baseline. Notably, MAD-RAG rectifies up to 74.68% of failure cases with negligible computational overhead.

阅读与讨论 → 访问原文 →
23.
arXiv (math.PR) 2026-06-16

A 0-1 Law for Multifractal Spectra via the HGDS Scale Derivative

作者:
Jokubas Petkevi\v{c}ius↗

arXiv:2606.15850v1 Announce Type: new Abstract: We prove that the multifractal spectrum D(h,omega) of a stochastic process is almost surely deterministic under a scale decorrelation condition on the HGDS scale derivative. The key difficulty is that the pointwise Hölder exponent lives in the germ sigma-algebra, where classical 0-1 laws do not reach. We get around this by working with the geometry accumulation integral G_Lambda, which is a genuine Lebesgue integral over scales and concentrates almost surely. The boundary case – log-correlated fields – is sharp: the variance summability condition fails exactly there.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.AI) 2026-06-24

AI Tokenomics: The Economics of Tokens, Computation, and Pricing in Foundation Models

作者:
Quanyan Zhu↗

arXiv:2606.24616v1 Announce Type: new Abstract: Tokens have become the practical accounting unit for modern foundation model services, linking information processing, computation, memory use, energy expenditure, pricing, and economic value. This paper develops a framework for AI tokenomics: the study of how tokens are generated, consumed, priced, allocated, and optimized across AI systems. We connect token-level technical costs to workflow-level production functions, enterprise resource allocation, measurement and instrumentation methods, and emerging market-design questions. The framework shows that token expenditure and economic value are distinct: value depends on marginal productivity, workflow position, hidden reasoning activity, risk, and downstream propagation effects. The paper concludes by identifying open research directions in hidden-token measurement, empirical calibration, token productivity, dynamic allocation, and token-based markets.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CV) 2026-06-11

RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers

作者:
Ruitong Sun↗Tianze Yang↗Wei Niu↗Jin Sun↗

Diffusion Transformers (DiTs) have achieved remarkable success in image generation, yet their deployment is hindered by high computational costs. We identify two sources of redundancy. First, temporal redundancy: Classifier-Free Guidance (CFG) applies costly dual forward passes at every timestep, yet guidance matters only at specific steps, and variable scales at critical steps can compensate for skipping others. Second, spatial redundancy: under variable guidance, different transformer blocks exhibit heterogeneous sensitivity, yet uniform calibration across all blocks wastes computation while failing to address their varying requirements. We present RSTR, the first framework to jointly reduce spatiotemporal redundancy in diffusion transformers. Stage-1 addresses temporal redundancy through evolutionary search, discovering sparse guidance schedules with variable scales. Stage-2 addresses spatial redundancy through adaptive rank allocation, assigning calibration capacities to transformer regions based on their sensitivity. Experiments on DiT-XL/2, PixArt-$\alpha$, FLUX, and state-of-the-art Qwen-Image demonstrate 50%-70% compute savings while maintaining or improving quality. On DiT-XL/2, RSTR achieves 57% savings with 15% FID improvement; on Qwen-Image, 3.43$\times$ speedup with preserved quality.

阅读与讨论 → 访问原文 →