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.CV) 2026-06-25

Entropy-Based Observability for AI Agent Behavior

作者:
Olasimbo Ayodeji Arigbabu↗

AI agents are typically instrumented through outcome-oriented indicators such as task success, reward, latency, and cost.Although these indicators are operationally important, they provide limited visibility into the internal structure of agent behavior such as the degree of exploration, the rigidity or diversity of action selection, the concentration of tool use, the reduction of uncertainty across a run, and the stability of behavior across repeated executions.This paper proposes Entropy-Based Observability for AI Agents (EOA), a lightweight framework for deriving behavioral telemetry from agent traces.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-17

A Multifaceted Analysis of Social Biases in Large Language Models

作者:
Xulang Zhang↗Rui Mao↗Erik Cambria↗

Large language models (LLMs) have rapidly become indispensable tools for acquiring information and supporting human decision-making. However, ensuring that these models uphold fairness across varied contexts is critical to their safe and responsible deployment. In this study, we undertake a comprehensive examination of four widely adopted LLMs, probing their underlying biases and inclinations across the dimensions of politics, ideology, alliance, language, and gender. Through a series of carefully designed experiments, we investigate their political neutrality using news summarization, ideological biases through news stance classification, tendencies toward specific geopolitical alliances via United Nations voting patterns, language bias in the context of multilingual story completion, and gender-related affinities as revealed by responses to the World Values Survey. Results indicate that while the LLMs are aligned to be neutral and impartial, they still show biases and affinities of different types.

阅读与讨论 → 访问原文 →
03.
arXiv (quant-ph) 2026-06-16

Generalized symmetries, invariant solutions and conservation laws in the Jaynes-Cummings model

作者:
Luis M. Pi\~nuelas↗Pablo C. L\'opez V\'azquez↗Alexander Yakhno↗

arXiv:2606.15538v1 Announce Type: cross Abstract: In this work, we investigate the Jaynes–Cummings model (JCM) using Lie symmetry analysis and conservation-law theory. The dynamics is formulated as a system of partial differential equations by projecting the von Neumann equation onto the atomic degrees of freedom and representing the field mode through its characteristic function. We determine the admitted point and generalized symmetries and construct invariant solutions satisfying the physical conditions imposed by quantum mechanics. The conventional dressed-state dynamics is recovered while a second class of solutions with radial dependence expressed through Heun polynomials is obtained for coupled atom–field configurations. We also apply the generating functions methodology to derive local conservation laws of the JCM differential system. Besides recovering the conservation of the total number of excitations, we obtain additional conserved currents involving atomic populations, coherence, reduced-state purity, and moments of the field characteristic function. In particular, we derive a balance equation for a combination of atomic purity and coherence whose evolution is controlled by the atom–field coupling and is linked to atom–field correlation and entanglement dynamics. The symmetry structure further generates generalized symmetries and an infinite hierarchy of conservation laws.

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

Purely unrectifiable sets, fractal percolation and graphs of functions

作者:
Zolt\'an Buczolich↗

arXiv:2606.15745v1 Announce Type: cross Abstract: This paper contains a survey of some of the results of the author related to unrectifiablity and is an extended version of the author's talk given at the Second Winter School Geometric Measure Theory Rectifiability vs. Pure Unrectifiability in Hanghzou, China. These results include irregular/purely unrectifiable $1$-sets on the graphs of continuous functions like the Takagi, the Weierstrass-Cellerier and the typical (in the sense of Baire) continuous function. It is also discussed that there exists $ {\alpha}_{0}\alpha_0$. The background of the $1$-unrectifiability is discussed in more detail.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-16

Green AI Carbon Optimizer: Carbon-Efficient Training Location Recommendation and Global AI Energy Demand Forecasting

作者:
Yuxin Chen↗Hao Gao↗Chujie Zou↗

arXiv:2606.14707v1 Announce Type: cross Abstract: AI training and deployment consume substantial electricity, but carbon outcomes remain weakly integrated into routine model development decisions. This paper presents Green AI Carbon Optimizer with two primary contributions: (i) a carbon aware cloud region recommendation method for training workloads, and (ii) a power law forecasting pipeline for global AI energy demand. For location recommendation, we combine regional grid carbon intensity, renewable share, and data center Power Usage Effectiveness (PUE) into a unified scoring model across 100+ regions from major cloud providers. For a reference workload (8*A100, 100h), estimated emissions in our sampled regions range from 7.74kg to 272.00kg CO2. Selecting the best region instead of the worst corresponds to a 97.2% reduction relative to the worst case. Ablation shows that ranking by renewable share alone can select regions with higher CO2 emissions than rankings that include grid carbon intensity. For forecasting, we fit a power law relation between parameter count and training energy using 26 anchor models. We combine this fit with scenario assumptions on model growth, hardware efficiency, and training frequency, and evaluate sensitivity to inference ratio and ecosystem scaling. Across scenarios, projected 2030 demand ranges from 7TWh to 1,436TWh under the stated assumptions, highlighting the importance of deployment choices, model scaling discipline, and transparent energy reporting.

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

High-Frequency Pricing at Scale for E-Commerce

作者:
Stefan Birr↗Tobias Huelden↗Mones Raslan↗Adele Gouttes↗Andreas Schmitt↗Mateusz Koren↗Johannes Stephan↗Robert Streek↗Manuel Kunz↗Tim Januschowski↗

arXiv:2606.13741v1 Announce Type: new Abstract: This paper presents the design, development, and implementation of a specialized forecast-then-optimize algorithmic pricing tool for sales campaigns in fashion e-commerce. Sales events present unique challenges for pricing including volatile demand patterns, rapid pricing decisions, and the need to balance short-term revenue with long-term profitability. We describe our approach combining daily-resolution demand forecasting using gradient-boosted trees with a multi-objective optimization framework that maximizes both long-term profit and net merchandise value for more than 5 million articles. Our solution addresses key limitations of existing weekly-granularity systems by implementing a forecast-then-optimize architecture that reduces pricing decision time from hours to minutes. We validate our approach through 23 A/B tests across 12 markets during 2023-2024 sales campaigns at Zalando, one of Europe's leading online fashion retailers. Experimental results demonstrate that the new pricing system achieves approximately 6% higher profit while maintaining equivalent performance on sales and revenue compared to the previous manual-algorithmic hybrid approach. Based on these results, the algorithm was successfully deployed to production and now handles the majority of algorithmic pricing decisions for sales campaigns at the company.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.CV) 2026-06-19

CalTennis: Large Multi-View Tennis Video Dataset and Benchmark of Monocular-to-3D Pose Estimation

作者:
Ilona Demler↗Xinran Xie↗Blake Werner↗Anna Szczuka↗Pietro Perona↗

The Caltech Tennis Dataset (CalTennis) is a large-scale video benchmark for evaluating monocular-to-3D pose estimation in the wild. CalTennis comprises over 11 million frames (51 hours) of tennis practice and match play from 40 players, captured with 2-6 synchronized cameras at 60 Hz. It is 10 times larger than existing in-the-wild human motion video datasets and 3 times larger than existing MOCAP-ground-truthed datasets, and it is the first large-scale benchmark to provide synchronized multi-view recordings of expert athletic motion. The multi-view setup enables inexpensive, label-free evaluation of monocular-to-3D pose estimation algorithms. We describe a simple, standardized protocol that enables data collection without specialized equipment or expertise, along with fully automated video calibration and synchronization. Benchmarking state-of-the-art monocular-to-3D pose methods on CalTennis, we find that while 3D joint angle recovery is now quite accurate, all models struggle to estimate depth and foot contact consistently. We further propose two novel performance metrics, footwork and stability, as well as qualitatively study body shape inconsistency. These metrics expose previously underexplored failure modes and point to concrete opportunities for improvement in pose estimation and action analysis.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.AI) 2026-06-17

DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue

作者:
Guillermo Gil de Avalle↗Laura Maruster↗Shaina Raza↗Christos Emmanouilidis↗

arXiv:2606.17904v1 Announce Type: new Abstract: Language models increasingly serve as advisory systems in maintenance operations. To prevent hallucination, recent systems ground these models in procedural documentation to constrain them to approved steps. In practice, however, operator queries frequently stray from this path, requiring models to recognise out-of-scope inputs mid-conversation, a dynamic that current benchmarks rarely prioritise. We introduce DiagFlowBench, a dataset of 50 industrial diagnostic flowcharts from a consumer manufacturer converted into 1,676 multi-turn conversations that contrast compliant with out-of-scope utterances. Evaluating a panel of ten commercial and open-weight models reveals high variability in abstention rates, with models commonly selecting a real but contextually inadequate step rather than fabricating facts. The inherent plausibility and authority of this mapped but wrong advice exposes a challenging vulnerability for grounding systems.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.AI) 2026-06-16

A Multi-Level Architecture for Reusable Materials Ontologies – The OntoCrafter Ceramics Ontology (OCO) as Reference Implementation

作者:
Thomas Pannek↗Wolfgang Grond↗

arXiv:2606.14814v1 Announce Type: cross Abstract: The Materials Science and Engineering ontology landscape is fragmented along multiple axes simultaneously. Horizontally: a recent survey identified 94 ontologies of which over 40 are structurally incompatible; each new application domain – ceramics, polymers, batteries, smart materials – typically restarts ontology design from scratch. Vertically: EU regulation (CSRD, CSDDD, PPWR, CBAM, R2R, AI Act, ESPR) forces material, manufacturing, supply-chain, and lifecycle data into integrated digital product passports, leaving ontologies that only address horizontal fragmentation incomplete for any contemporary consumer. And mechanistically: a vocabulary that records that BNT-BT has $d_{33} \approx 580$ pC/N stores a fact but cannot surface why – Bi-6s$^2$ lone-pair stereo-activity, anomalous Born effective charges, soft modes, defect chemistry – without a systematic explanation skeleton. We propose a multi-level modular architecture with two independent classification axes – level of abstraction (L0 bridges, L1 material-agnostic laboratory-notebook, L2 material-class-specific, L3 categorical reasoning) and consumer audience (material vs. compliance) – in which the material-specific level is internally organised by a seven-tier mechanistic-explanation skeleton (Symmetry, Energy/DFT, Thermo/CALPHAD, Kinetics, Microstructure, Defect chemistry, Bonding) applicable to any crystalline ionic oxide. The level-and-audience modularity dissolves the horizontal fragmentation, the compliance audience absorbs the vertical regulation pressure, and the seven-tier organisation of Level 2 delivers the mechanistic explanation depth. We instantiate the architecture as the OntoCrafter Ceramics Ontology (OCO v0.94): 5,196 classes across 44 modules; 167,348 OWL axioms (40,454 logical); 1,674 properties; 829 cross-ontology bridge mappings; 1,172 SHACL shapes; 163 published competency questions.

阅读与讨论 → 访问原文 →
10.
arXiv (quant-ph) 2026-06-25

Quantum Error Correction-like Noise Mitigation for Wave-like Dark Matter Searches with Quantum Sensors

作者:
Hajime Fukuda↗Takeo Moroi↗Thanaporn Sichanugrist↗

arXiv:2511.03253v2 Announce Type: replace-cross Abstract: We propose a quantum error correction-like noise mitigation protocol for enhancing the sensitivity of wave-like dark matter searches with quantum sensors. Our protocol uses multiple sensors to mitigate the noise affecting each sensor individually, allowing for the suppression of excitation noise that is parallel to the dark matter signal. We demonstrate that our protocol can improve the sensitivity to dark matter signals by a factor of $\sqrt{N}$, where $N$ is the number of sensors used, for small $N$. Furthermore, for sufficiently large $N$, we find that our protocol achieves the same performance as the standard quantum limit by the ideal measurement, which non-entangled sensors with parallel noise cannot reach due to the unknown phase of the dark matter field. Our work can be widely applied to various types of signals with unknown phases, and has the potential to enhance the sensitivity of quantum sensors such as arrays of resonant cavities.

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

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

作者:
Stipe Frkovic↗Metod Jazbec↗Dan Zhang↗Christian A. Naesseth↗Ilija Bogunovic↗Eric Nalisnick↗

arXiv:2606.12232v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation. A notable limitation of the masked formulation, however, is that once a token has been unmasked it can no longer be revised, leaving dLLMs vulnerable to early sampling mistakes. To address this, a growing body of work has sought to extend masked dLLMs with self-correcting (remasking) capabilities. One appealing subset of these methods does so in a training-free, post-hoc manner based on token confidences, with encouraging early reported results. In this work, we revisit the empirical evaluation of a representative post-hoc remasking method, WINO [Hong et al., 2026], and find that under standard decoding settings (shorter block lengths) it brings little-to-no benefit over confidence-based unmasking alone [Wu et al., 2025]. Extending the evaluation to non-greedy decoding, we find that while confidence-based remasking can mitigate errors introduced by increased stochasticity to some extent, it also exacerbates the diversity collapse previously reported for confidence-based unmasking. Overall, our results show that the benefits of post-hoc confidence-based remasking are highly setting-dependent, underscoring the need for a more comprehensive evaluation framework.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CV) 2026-06-25

Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines

作者:
Duy Tran Thanh↗

Production vision pipelines silently degrade on blurry input, wasting compute on downstream OCR, retrieval, and vision-language model (VLM) calls that cannot recover a usable output. We present MagikaDocumentFromPixel, a lightweight, CPU-friendly image quality gate that classifies a single image as sharp, blurred, or uncertain in roughly 7 ms on a single CPU core. The contributions are (i) a recipe selected from a 46-configuration, 8-sweep empirical search that isolates input resolution as the dominant lever and shows architecture capacity only pays off at >= 384 px; (ii) a confidence-aware routing formalism grounded in classical selective prediction; (iii) the Edge Prior Module (EPM), a Laplacian-magnitude auxiliary input channel that gives the network direct access to the spectral evidence that classical blur heuristics rely on and that lifts test F1 by +1.3 points in a matched-env comparison; and (iv) an observation that the gate is one instance of a recurring design pattern that appears independently in Magika content-type detection, risk-controlled OCR with VLMs, and DocVLM. The final recipe MobileNetV3-Large with the EPM trained at 384x384 on paired GoPro Large frames, evaluated with 5-scale test-time augmentation reaches F1 = 0.9803 (AUC 0.9989) with a 17 MB ONNX artifact, improving over our fixed-scale baseline on the same hardware (F1 = 0.9672) by +1.31 points. We are explicit about limitations: results are on a single motion-blur distribution, numbers are from a single seed, and calibration is qualitative rather than measured.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CV) 2026-06-18

Spatially Stratified Distillation for Heterogeneous Radar Place Recognition

作者:
Sagun Singh Shrestha↗Samuel Harding↗Abdelwahed Khamis↗Saimunur Rahman↗Peyman Moghadam↗

Scalable, all-weather place recognition increasingly relies on heterogeneous radar place recognition to bridge diverse hardware platforms. A notable application is matching queries from cost-effective 4D automotive radars against high-fidelity reference maps built by dense spinning radars. This process is fundamentally limited by the extreme sparsity (and narrow field-of-view) of the 4D sensor, which captures only a fraction of the structural density present in the spinning radar database. Prior efforts address this issue by unifying different radar signals. That is, projecting both signals into a common representational space. Yet, they suffer performance degradation in multi-session environments. In this paper, we propose spatially-stratified distillation (SSD); a strategy that replaces standard uniform distillation with an asymmetric spatial alignment derived directly from physical radar returns. In regions where both radars exhibit overlapping returns, SSD enforces strong feature alignment. Crucially, in sparse regions where the 4D student lacks returns but the teacher contains valid structure within the shared field of view, SSD applies heavily discounted distillation weights. Extensive evaluations of the recent HeRCULES dataset demonstrate that SSD significantly outperforms prior place recognition methods, achieving state-of-the-art results on its challenging dynamic sequences.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.CV) 2026-06-11

MedCTA: A Benchmark for Clinical Tool Agents

作者:
Tajamul Ashraf↗Hyewon Jeong↗Fida Mohammad Thoker↗Bernard Ghanem↗

To make clinically grounded decisions, medical AI agents are expected to go beyond simple recognition and be capable of tool retrieval, evidence acquisition, and integration. Existing benchmarks largely evaluate isolated perception or single-turn question answering, and therefore provide limited visibility into failures of planning, tool recruitment, and rollout reliability. We introduce MedCTA, a benchmark for evaluating medical tool agents on clinician-validated, step-implicit tasks grounded in realistic multimodal clinical inputs, including radiology images, pathology slides, and reports. MedCTA comprises 107 real-world clinical tasks with clinician-verified executable trajectories over 5 deployed tools, and supports process-aware evaluation of tool selection, argument validity, execution stability, trajectory fidelity, and outcome quality. We benchmark 18 open- and closed-source multimodal models and find that even frontier systems remain brittle in multi-step clinical tool use: autonomous rollouts are dominated by protocol failures, premature stopping, and incorrect tool recruitment, while gold-standard tool routing yields large but still incomplete gains. These results show that strong backbone perception does not translate into reliable agentic behavior in clinical settings. MedCTA provides a rigorous testbed for auditing, diagnosing, and advancing trustworthy medical AI agents. The dataset and evaluation suite are available at https://ivul-kaust.github.io/MedCTA/

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CV) 2026-06-16

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

作者:
Han Sun↗Qin Li↗Peixin Wang↗Min Zhang↗

Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous driving and medical image analysis. Through systematic empirical investigation, we identify that the imbalanced attention allocation, both across modalities (i.e., vision and language) and within modalities (among individual tokens), exhibits a strong causal correlation with the occurrence of object hallucination. Leveraging this insight, we introduce a novel concept termed attention imbalance, which not only quantifies the degree of attention disparity but also visually delineates the underlying patterns (e.g., over-attentiveness to irrelevant language tokens or under-attentiveness to discriminative visual features) that drive object hallucination. To mitigate object hallucination, we further propose Attention Imbalance Rectification (AIR), a lightweight decoding-time intervention method that reallocates attention weights and adjusts attention distributions to rectify modality-wise and token-wise imbalances. Extensive evaluations on four mainstream LVLMs and three benchmarks (CHAIR, POPE, and MM-Vet) with seven baselines demonstrate that AIR consistently reduces object hallucination rates, achieving up to a 35.1% reduction compared to the baselines, while improving up to 15.9% of LVLMs' general capability across diverse vision-language tasks.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.CV) 2026-06-25

Minimalist Preprocessing Approach for Image Synthesis Detection

作者:
Hoai-Danh Vo↗Trung-Nghia Le↗

Generative models have significantly advanced image generation, resulting in synthesized images that are increasingly indistinguishable from authentic ones. However, the creation of fake images with malicious intent is a growing concern. Low-configured smart devices have become highly popular, making it easier for deceptive images to reach users. Consequently, the demand for effective detection methods is increasingly urgent. In this paper, we introduce a simple yet efficient method that captures pixel fluctuations between neighboring pixels by calculating the gradient, which highlights variations in grayscale intensity. This approach functions as a high-pass filter, emphasizing key features for accurate image distinction while minimizing color influence. Our experiments on multiple datasets demonstrate that our method achieves accuracy levels comparable to state-of-the-art techniques while requiring minimal computational resources. Therefore, it is suitable for deployment on low-end devices such as smartphones. The code is available at https://github.com/vohoaidanh/adof.

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

LADBench: A Benchmark for Logical Fault Detection in Images

作者:
Sahasra Kondapalli↗Lara Radovanovic↗Aadi Palnitkar↗Mingyang Mao↗Xiaomin Lin↗

Large Vision Language Models (VLMs) excel at visual question answering and semantic grounding, but their capacity for autonomous logical reasoning remains underexplored. Existing anomaly benchmarks emphasize visual errors or direct prompting rather than the physical and social common sense needed for open-world deployment. To address this, we introduce LAD-bench, a benchmark of more than 1,000 curated synthetic images with logical anomalies across four domains: Residential, Urban, Collaborative, and Nature. We further propose a Tiered Prompting Protocol based on progressive disclosure, which measures how much explicit assistance a model needs to localize and reason about a logical fault. Evaluating leading foundation models reveals substantial weaknesses: even the best achieves only 70.11% overall accuracy, showing that implicit logical fault detection remains unsolved. Crucially, models often fail to identify anomalies even after receiving explicit hints in deeper tiers. By surfacing these limitations in sequential multimodal reasoning, LAD-Bench offers a rigorous framework for advancing the safety, reliability, and cognitive alignment of autonomous visual systems. Dataset and Code: https://huggingface.co/datasets/SahasraK/LADBench

阅读与讨论 → 访问原文 →
18.
arXiv (CS.CL) 2026-06-12

Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science

作者:
Varun Kotte↗

LLM annotators are increasingly used in computational social science (CSS), but it is unclear whether their alignment-shaped errors preserve the empirical conclusions a researcher would report. We audit three open-source 7B instruction-tuned models (Zephyr, Mistral-Instruct, Qwen2.5-Instruct) across six TweetEval tasks under four prompt conditions (72 cells) and find that social-desirability failures do not run in a single direction. Zephyr exhibits leniency bias, systematically under-applying harmful labels (offensive language: false benign rate 0.729, false alarm rate 0.031). Mistral and Qwen exhibit overcorrection, over-applying the same labels (Mistral hate-speech FAR = 0.604). All three models exhibit neutrality bias on abortion stance, underestimating opposition prevalence by 24 to 40 percentage points and inflating the neutral label. None of the four prompting interventions we test (neutral, safety framing, depersonalized, chain-of-thought) corrects these failures across models; safety framing can worsen stance distortion. Strikingly, Zephyr's hate-speech prevalence estimate matches the gold rate exactly while its class-conditional errors are large in both directions, an accidental cancellation that misleads aggregate validation. We translate these patterns into a three-part taxonomy with diagnostic FBR/FAR signatures and a lightweight gold-sample validation protocol. The headline for trustworthy CSS: a model that looks calibrated on aggregate metrics can still flip the substantive empirical conclusion a researcher would report.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.CL) 2026-06-16

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

作者:
Yuyao Wang↗Zhongjian Zhang↗Mo Chi↗Kaichi Yu↗Yuhan Li↗Miao Peng↗Bing Tong↗Chen Zhang↗Yan Zhou↗Jia Li↗

Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability remains under-evaluated, largely because existing benchmarks do not provide a systematic way to assess memory mechanisms. In this paper, we study agent memory from a self-evolving perspective and introduce EvoMemBench, a unified benchmark organized along two axes: memory scope (in-episode vs. cross-episode) and memory content (knowledge-oriented vs. execution-oriented). We compare 15 representative memory methods with strong long-context baselines under a standardized protocol. Results show that current memory systems are still far from a general solution: long-context baselines remain highly competitive, memory helps most when the current context is insufficient or tasks are difficult, and no single memory form works consistently across all settings. Retrieval-based methods remain strong for knowledge-intensive settings, whereas procedural and long-term memory methods are more effective for execution-oriented tasks when their stored experience matches the task structure. We hope EvoMemBench facilitates future research on more effective memory systems for LLM-based agents. Our code is available at https://github.com/DSAIL-Memory/EvoMemBench.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-12

Cross-Model Disagreement as a Label-Free Correctness Signal

作者:
Matt Gorbett↗Suman Jana↗

arXiv:2603.25450v2 Announce Type: replace Abstract: Detecting when a language model is wrong without ground truth labels is a fundamental challenge for safe deployment. Existing approaches rely on a model's own uncertainty – such as token entropy or confidence scores – but these signals fail critically on the most dangerous failure mode: confident errors, where a model is wrong but certain. In this work we introduce cross-model disagreement as a correctness indicator – a simple, training-free signal that can be dropped into existing production systems, routing pipelines, and deployment monitoring infrastructure without modification. Given a model's generated answer, cross-model disagreement computes how surprised or uncertain a second verifier model is when reading that answer via a single forward pass. No generation from the verifying model is required, and no correctness labels are needed. We instantiate this principle as Cross-Model Perplexity (CMP), which measures the verifying model's surprise at the generating model's answer tokens, and Cross-Model Entropy (CME), which measures the verifying model's uncertainty at those positions. Both CMP and CME outperform within-model uncertainty baselines across benchmarks spanning reasoning, retrieval, and mathematical problem solving (MMLU, TriviaQA, and GSM8K). On MMLU, CMP achieves a mean AUROC of 0.75 against a within-model entropy baseline of 0.59. These results establish cross-model disagreement as a practical, training-free approach to label-free correctness estimation, with direct applications in deployment monitoring, model routing, selective prediction, data filtering, and scalable oversight of production language model systems.

阅读与讨论 → 访问原文 →
21.
arXiv (quant-ph) 2026-06-25

Wide-field NV magnetometry under simultaneous high-pressure and high-temperature conditions

作者:
Masahiro Ohkuma↗Eikichi Kimura↗Shumpei Ohyama↗Miu Tezuka↗Ryo Matsumoto↗Shinobu Onoda↗Yoshihiko Takano↗Shintaro Azuma↗Kenji Ohta↗Keigo Arai↗

arXiv:2606.25378v1 Announce Type: cross Abstract: We demonstrate wide-field optically detected magnetic resonance (ODMR) under simultaneous high-pressure and high-temperature conditions using nitrogen-vacancy (NV) centers. Although NV-center magnetometry has been widely used for spatially resolved magnetic-field imaging, its application to extreme environments combining pressure and temperature remains challenging. In this work, we show that ODMR can be observed at 5 GPa and 500 K, demonstrating the feasibility of NV spin readout under such combined extreme conditions. We further perform wide-field ODMR of iron at 7 GPa and 500 K, where the stray magnetic field from the sample is spatially visualized through the pressure cell. These results establish NV-center magnetometry as a promising platform for imaging magnetic phenomena in materials under high-pressure and high-temperature environments.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.AI) 2026-06-11

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

作者:
Subbarao Kambhampati↗Karthik Valmeekam↗Siddhant Bhambri↗Vardhan Palod↗Lucas Saldyt↗Kaya Stechly↗Soumya Rani Samineni↗Durgesh Kalwar↗Upasana Biswas↗

arXiv:2504.09762v4 Announce Type: replace Abstract: Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} – implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous – it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CL) 2026-06-18

Possible or Definite? A Benchmark for Evaluating Diagnostic Uncertainty Preservation in Clinical Text

作者:
Hongbo Du↗Zixin Lu↗Jiaming Qu↗

Large language models (LLMs) are increasingly used for clinical text tasks such as summarization and revision. While most studies evaluate the fluency and coherence of LLM-generated text, whether LLMs correctly preserve diagnostic uncertainty remains underexplored. In clinical practice, phrases such as ``possible pneumonia'' communicate the strength of available evidence and directly guide decisions about follow-up testing and treatment. Altering these uncertainty expressions can change the clinical meaning entirely. In this paper, we systematically evaluated this problem in two steps. First, we constructed a benchmark of 1,200 clinical documents with 9,184 uncertainty annotations across five levels. Second, we evaluated three LLMs on this benchmark. Our results show that (1) LLMs preserve the original uncertainty cues poorly, often less than half the time; (2) LLMs struggle with nuanced distinctions between adjacent levels. This work reveals a failure mode not captured by standard evaluation metrics and provides implications for the safe deployment of LLMs in clinical workflows.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CV) 2026-06-25

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

作者:
Cong Chen↗Guo Gan↗Kaixiang Ji↗ZhaoYang Zhang↗Zhen Yang↗Guangming Yao↗Hao Chen↗Jingdong Chen↗Yi Yuan↗Chunhua Shen↗

Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a Hierarchical Graph Memory, a top-down three-tier architecture for semantic abstraction, anchored by a foundational graph capturing spatiotemporal and causal relations. During inference, the reasoning model employs agentic tool-augmented retrieval, navigating hierarchies, searching nodes, and traversing logical edges via an Observation-Reason-Action loop. Experiments show MemDreamer achieves SOTA results across four mainstream benchmarks, narrowing the gap with human experts to only 3.7 points. It constrains the reasoning context window to merely 2% of full-context ingestion while delivering a 12.5 point absolute accuracy gain. Furthermore, statistical analysis uncovers a strong positive linear correlation between an VLM's performance on logic reasoning and long-video understanding benchmarks, establishing agentic capability scaling as a new paradigm for multimodal comprehension.

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

SG2Loc: Sequential Visual Localization on 3D Scene Graphs

作者:
Nicole Damblon↗Olga Vysotska↗Federico Tombari↗Marc Pollefeys↗Daniel Barath↗

Visual localization in complex indoor environments remains a critical challenge for robotics and AR applications. Sequential localization, where pose estimates are refined over time, is important for autonomous agents. However, traditional methods often require storing extensive image databases or point clouds, leading to significant overhead. This paper introduces a novel, lightweight approach to sequential visual localization using 3D scene graphs. Our method represents the environment with a compact scene graph, where nodes represent objects (with coarse meshes) and edges encode spatial relationships. For each image in the localization phase, we extract per-patch semantic features, predicting object identities. Localization is performed within a particle filter framework. Each particle, representing a camera pose, projects the coarse object meshes from the scene graph into the image, assigning object identities to patches based on visibility. The similarity of the per-patch features, in the input image, and object features from the scene graph determines the weight of a particle. Subsequent images are incorporated sequentially, refining the pose estimate. By leveraging a compact scene graph and efficient semantic matching, our method significantly reduces storage while maintaining performance on real-world datasets. The code will be available at https://github.com/DmblnNicole/sg2loc.

阅读与讨论 → 访问原文 →