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 (CS.LG) 2026-06-16

Latent space mapping of interpretable structural coordinates from stochastic single-molecule signals

arXiv:2606.16950v1 Announce Type: cross Abstract: Nanopores are versatile single-molecular sensors, but their utility is fundamentally constrained by stochastic translocation dynamics warping any encoded information. We resolve it by shifting from time-domain analysis to a learned latent-space mapping via a contrastive encoder trained exclusively on simulated signals from a physics-informed model. This encoder maps solid-state nanopore signals of engineered DNA barcodes into an interpretable molecular coordinate system. The learned representation is responsive to structural barcode parameters while remaining invariant to acquisition conditions and translocation conformation, allowing data pooling across devices. Molecule identification requires a single pass through the encoder, reducing computational cost by three orders of magnitude relative to alignment-based methods. We experimentally validate through mixture quantification, rare-variant detection, consensus barcode reconstruction, and real-time signal acquisition. This shift from temporal analysis to mapping structural coordinates into a latent space changes the paradigm behind analyzing stochastic sensor signals by linking classification to interpretable encoded molecular information.

02.
arXiv (CS.CL) 2026-06-11

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

作者:

Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main challenge is that most studies treat the poetic appreciation task as a general-domain problem, neglecting the distinctive features of poetic appreciation, while high-quality and domain-specific datasets are extremely limited. To address this limitation, we decompose the task into three subtasks: term interpretation, semantic interpretation, and emotional inference. Based on multiple open-source datasets, we perform data cleansing and alignment to construct the Classical Chinese Poetry Instruction Pair Dataset (CCPoetry-49K), which comprises 49,404 high-quality instruction-response pairs explicitly optimized for this domain. We then propose a domain-specialized LLM, called PoetryQwen, by applying Low-Rank Adaptation (LoRA) to fine-tune the Qwen2.5-14B model. Experimental results on the CCL25-Eval Task 5 benchmark demonstrate that PoetryQwen achieves a score of 0.757, representing a 9.7% improvement over the Qwen2.5-14B-Instruct baseline (0.690). These findings clearly indicate that PoetryQwen significantly enhances performance in precise translation and emotional understanding of classical poetry. We present new dataset and methodological considerations intended to support the domain-specific optimization of LLMs.

03.
arXiv (CS.AI) 2026-06-16

Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability

arXiv:2606.01365v2 Announce Type: replace Abstract: Failure-aware observability diagnoses wasted computation in multi-agent LLM systems before final-answer evaluation can explain what went wrong. We propose a trace-based framework for a three-agent architecture – orchestrator, search agent, and execution agent – that converts structured events into online signals for loops, budget pressure, low information gain, and tool instability, then adds offline semantic grounding metrics and selective LLM-as-judge evaluation. On 165 GAIA validation traces under identical caps, 98 runs produce usable final answers and 67 fail or stop without one. Among warned failed runs, 58.1% of tokens are spent after the first warning on average, indicating substantial opportunity for intervention. A 10-task Level-2 pilot uses warnings to diversify search or require evidence, reducing post-warning token fraction from 0.638 in the baseline to 0.304. The results support a layered design: cheap online signals help the orchestrator redirect or halt redundant behavior, while deeper semantic checks identify whether completed answers are grounded enough to trust.

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

RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models

arXiv:2606.18950v1 Announce Type: new Abstract: Modern Vision-Language Models (VLMs) often struggle with strategic reasoning, i.e., anticipating and influencing other agents' actions, under uncertainty in competitive and cooperative settings. Real-time strategy (RTS) games can be a natural testbed for diagnosing this limitation, as they demand coordination with allies, adaptation to opponents' strategy, and long-horizon planning under partial observability. However, existing RTS benchmarks offer limited evaluation scope, lack systematic competency diagnosis, and remain fixed in the pre-designed scenario coverage. To address these limitations, we present RTSGameBench, which is built on Beyond All Reason, a large-scale RTS game with an expanded battlefield that demands broader strategy diversity than the existing testbeds. The proposed benchmark provides evaluations through diverse gameplay across various matchup structures, diagnostic assessment via mini-games, each targeting an individual strategic competency, and extensible coverage via a self-evolving generation framework that converts free-form queries into new mini-games, improving over successive cycles. Additionally, for VLMs to operate in large-scale RTS games, we provide RTSGameAgent that manages units by an FSM with agentic memory. We empirically validate that multiple state-of-the-art VLMs do not perform well when matchups demand tighter coordination, multiagent coordination and when task scale increases.

06.
medRxiv (Medicine) 2026-06-15

Specialty Choice Attitudes Among Medical Interns: Evidence from Hormozgan University of Medical Sciences

Background: Choosing a medical specialty is a critical career decision that affects both physicians future professional lives and the composition of the healthcare workforce. Specialty preferences are shaped by multiple personal, educational, and socioeconomic factors, yet evidence from senior medical students in southern Iran remains limited. This study aimed to assess willingness to pursue specialty training among medical interns at Hormozgan University of Medical Sciences, identify their preferred specialties, and examine factors associated with their decisions. Methods: This descriptive-analytical cross-sectional study was conducted in 2023 among medical interns at Hormozgan University of Medical Sciences in Bandar Abbas, Iran. Using a convenience census approach, all eligible interns were invited to participate, and 83 students completed an online questionnaire. The instrument collected demographic, academic, and occupational data, as well as reasons for willingness or unwillingness to pursue specialty training and specialty preferences. Content and face validity were assessed by faculty members and students, and internal consistency reliability in the present study was acceptable (Cronbach alpha = 0.82). Data were analyzed using descriptive statistics and logistic regression in SPSS version 27. Results: Of the 83 participants, 50 (60.2%) reported willingness to pursue specialty training, while 33 (39.8%) did not. Among students willing to continue, the most frequently cited reasons were achieving a better economic position, broader job opportunities, and higher social status. Among those unwilling to continue, the most common reasons were fatigue from prolonged studying, financial problems, and the desire to start working after graduation. Radiology was the most common first-choice specialty, followed by otorhinolaryngology, dermatology, and cardiology. In regression analyses, no demographic or academic variable remained independently associated with willingness to pursue specialty training in the final multivariable model. Conclusions: A majority of medical interns were interested in pursuing specialty training, with preferences concentrated in a limited number of specialties perceived as offering favorable financial prospects, prestige, and lifestyle. Economic concerns and educational fatigue were the dominant factors influencing willingness and unwillingness to continue specialty education. These findings highlight the need for structured career counseling, broader exposure to different specialties, and policy measures to address financial and structural barriers to residency training. Keywords: medical specialty choice; medical interns; residency training; medical education; Hormozgan university of medical sciences

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

TS-Fault: Benchmarking Time Series Forecasters Against Structural Faults

arXiv:2606.18539v1 Announce Type: new Abstract: Time series forecasting (TSF) underpins consequential decisions in energy, transportation, finance, and healthcare, yet TSF models are almost universally ranked by a single number (e.g., average error) on clean held-out data, under the implicit assumption that it predicts deployed reliability. However, real faults are not i.i.d noise but structured events with temporal shape, broken cross-variable dependencies, regime change coupled with missingness, and causal propagation across a sensing pipeline. Treating TSF robustness as a data-quality problem, we present TS-Fault, a benchmark that evaluates forecasting models under explicit, parameterized fault scenarios with controllable semantic difficulty. TS-Fault organizes recurring failures into four modes along two orthogonal axes (observation- vs mechanism-level; univariate vs multivariate) and injects each fault into the most prediction-critical window via a unified importance score. This design enables robustness to be tested against the structures models actually rely on, rather than reduced to generic noise sensitivity. We evaluate 21 models across 6 datasets, 4 modes, and 5 difficulty levels under a paired clean/corrupt protocol. The results reveal three findings that contradict common leaderboard intuition: (i) clean-data accuracy anti-correlates with robustness; (ii) clean rankings are preserved under observation-level faults but reshuffled under mechanism-level faults; and (iii) all catastrophic failures occur under mechanism-level faults, with foundation models achieving the highest clean-data accuracy yet exhibiting the greatest fragility. The code is publicly available at https://github.com/Ray-zyy/TS-Fault.

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

Stochastic Thermodynamics and SDE-based Generative Models

作者:

arXiv:2606.18290v1 Announce Type: cross Abstract: SDE-based generative models, including diffusion models and the Schrödinger bridge, have found broad applications in signal processing tasks such as speech enhancement, image restoration, and time-series generation. This note presents a modeling framework for such models within the context of stochastic thermodynamics. The main results of this note are trajectory-level definitions of work, heat, and entropy production, along with a generalized Jarzynski identity and a second-law-like inequality. The proposed framework extends the original Jarzynski setup to accommodate time-dependent bath temperature and nonconservative driving forces. This thermodynamic perspective may deepen our understanding of diffusion models and the Schrödinger bridge from a nonequilibrium statistical mechanics viewpoint.

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

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction. Our framework derives an upper bound on the base model's expected risk using four measurable quantities: proxy risk, SAE reconstruction gap, concept-pool mismatch, and sparse complexity. We interpret this certificate as an operational criterion for explanatory faithfulness. In particular, a non-vacuous bound indicates that the extracted sparse features retain meaningful predictive information, while small reconstruction and mismatch errors indicate that the proxy remains behaviorally close to the original model. Empirically, we show that the bound becomes non-vacuous on GPT-2 Small, Gemma-2B, and Llama-3-8B at practical sample sizes. A detailed layerwise analysis of Llama-3-8B reveals a strong depth dependence, with later layers becoming much easier to certify, associated with both stronger local fidelity and weaker downstream error amplification. Finally, through feature-shuffling ablations, we show that the decomposition distinguishes genuine semantic alignment from mere statistical sparsity, providing a useful diagnostic for when SAE-based explanations become less reliable.

10.
arXiv (math.PR) 2026-06-18

The FBSDE approach to sine-Gordon up to $6\pi$

arXiv:2401.13648v3 Announce Type: replace-cross Abstract: We develop a stochastic analysis of the sine-Gordon Euclidean quantum field $(\cos (\beta \varphi))_2$ on the full space up to the second threshold, i.e. for $\beta^2 < 6 \pi$. The basis of our method is a forward-backward stochastic differential equation (FBSDE) for a decomposition $(X_t)_{t \geqslant 0}$ of the interacting Euclidean field $X_{\infty}$ along a scale parameter $t \geqslant 0$. This FBSDE describes the optimiser of the stochastic control representation of the Euclidean QFT introduced by Barashkov and one of the authors. We show that the FBSDE provides a description of the interacting field without cut-offs and that it can be used effectively to study the sine-Gordon measure to obtain results about large deviations, integrability, decay of correlations for local observables, singularity with respect to the free field, Osterwalder-Schrader axioms and other properties.

11.
arXiv (CS.CL) 2026-06-17

Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization

Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversational and spatial analysis but introduces security risks. This work presents a security-oriented framework for risk identification, evaluation, and mitigation in a multi-agent GIS system while maintaining adaptability to broader agentic architectures. We test the agentic system of a commercial geospatial partner while developing a modular state-machine-based orchestration framework that abstracts agent behavior into reusable components. We evaluate robustness using a red-teaming framework with an adaptive attacker LLM and a deterministic judge that produces binary outcomes with supporting rationales across multi-turn attacks. We further improve resilience with a prompt optimization framework that treats prompts as structured signatures and injects adversarial demonstrations, enabling systematic security improvements without degrading task performance.

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

Adaptive Nucleus Truncation for Long-Form Reasoning

arXiv:2606.13982v1 Announce Type: cross Abstract: Sampling plays an important role in long-form language-model reasoning. Over thousands of decoding steps, small changes in the candidate token set can compound into different reasoning trajectories, stability profiles, and final answers. Existing truncation methods such as top-$p$, min-$p$, and fixed top-$n\sigma$ sampling improve over unrestricted sampling, but they rely on fixed thresholds that cannot adapt to changes in entropy, task difficulty, training stage, or generation budget. We introduce Adaptive Nucleus Truncation Sampling (ANTS), which extends top-\(n\sigma\) sampling from a fixed decoding rule into an adaptive rollout-control mechanism for long-form generation. ANTS selects standardized neighborhoods around the maximum logit before temperature scaling, adapts the truncation width using an entropy-conditioned controller, and retains a no-truncation fallback arm to stabilize training when truncation becomes unsafe. On a 33B-total / 4B-active sparse Mixture-of-Experts reasoning model, ANTS improves average performance over percentage-based benchmarks by +1.9, +3.8, and +5.2 points at 8K, 16K, and 32K generation budgets, respectively. The strongest gains appear on instruction following and mathematical reasoning, with IFBench improving by more than 10 points at 32K and AIME 2025 improving by 7 points. Code generation reveals an important budget interaction. On Codeforces, ANTS trails the baseline at 8K, but reverses this gap and substantially improves ELO at 16K and 32K. These results suggest that sampler design should be treated not just as a decoding hyperparameter, but as part of how we stabilize and scale long-budget reasoning.

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

Stringalign: Moving beyond summary statistics with a transparent Unicode-aware tool for evaluating automatic transcription models

Comparing text strings is crucial when evaluating and understanding the performance of various text processing tasks such as document recognition and audio transcription. With an increasingly complex landscape of AI-based handwritten text recognition (HTR), optical character recognition (OCR) and automatic speech recognition (ASR) models, there is a need for tools that facilitate evaluation in a flexible and reproducible way. This paper presents Stringalign, a Python library designed to simplify the evaluation process for automatic transcription projects and facilitate transparent evaluation. Stringalign's tools to examine and visualise both the rate of errors and the types of errors a model makes, give insights into possible improvements and help inform model selection for a particular task. Widely used string comparison metrics, such as the character and word error rates (CER and WER), although useful, can be ambiguous due to varying definitions of what constitutes a character and a word. Stringalign addresses this challenge by ensuring all preprocessing (i.e. normalisation and tokenisation) is transparent and easily replicable, and by providing tools to move beyond summary statistics and analyse common model errors. Moreover, Stringalign adheres to FAIR (Findable, Accessible, Interoperable, and Reusable) principles for research software while staying lightweight and easy to adapt into researchers existing workflows. In this paper, we discuss challenges with character and word level string comparisons and show through examples that where existing tools can yield opaque and sometimes confusing results, Stringalign provides an easy-to-use and unambiguous alternative.

14.
medRxiv (Medicine) 2026-06-18

Evaluating Deep-Learning Based Quantification of Breast Arterial Calcification on Mammography for Cardiovascular Risk Assessment

Purpose: To develop and evaluate a deep learning model for automated quantification of breast arterial calcification (BAC) on screening mammography and to assess whether AI-derived BAC burden predicts major adverse cardiovascular events (MACE) in women. Methods: In this retrospective study, 202,006 women who underwent screening mammography without history of MACE were included. A BAC segmentation model was trained on an expert-annotated dataset using a multi-task U-Net with a ResNet-18 encoder to detect and segment BAC. BAC burden was quantified as area (mm{superscript 2}) from model-generated masks using DICOM pixel spacing and categorized by tertiles into low, intermediate, and high. The PREVENT score and incident MACE were identified from electronic health records. Cox proportional hazards models were developed to evaluate AI-derived BAC burden and PREVENT score alone, and combined models for 5 - and 10-year cardiovascular risk prediction. Results: Among 202,006 women (mean age 54.8{+/-}11.7 years), 23.1% had AI-detected BAC, and 7,701 (3.8%) developed incident MACE during a median follow - up of 7.5 years. On the geographically held-out test set, the BAC model achieved an AUROC of 0.97, Dice score of 0.6678, and Pearson correlation of 0.961 between AI-derived and manually annotated BAC burden. BAC burden increased with age and was higher among women who developed MACE. Five - year MACE incidence increased across BAC categories from 1.5% in women without BAC to 6.9% in those with high BAC burden. BAC burden alone showed modest prediction of MACE, with 5-year and 10-year AUROCs of 0.661 and 0.650, respectively, while PREVENT achieved AUROCs of 0.781 and 0.771. Adding BAC to PREVENT produced minimal improvement in discrimination. Conclusion: Deep learning-based BAC quantification from routine mammography is feasible, accurate, and associated with future cardiovascular risk. Although BAC added little to PREVENT for overall discrimination, it may serve as a scalable opportunistic imaging biomarker to identify women at elevated cardiovascular risk and support preventive care.

15.
arXiv (CS.CV) 2026-06-18

SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests

We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds. The model combines a serialization-based Point Transformer v3 backbone with a lightweight semantic head and a tree-focused cross-attention mask decoder. Semantic predictions restrict instance decoding to tree-class voxels, while instance-aware query initialization, one-to-many seed supervision, and asymmetric mask scoring improve separation in dense and structurally complex stands. We further introduce FOR-instance v3, an expanded benchmark comprising 427 scenes and 26,496 annotated trees across diverse biomes, forest structures, and LiDAR platforms. On the FOR-instanceV2 test split, SegmentAnyTreeV2 achieves 90.5% precision, 80.2% recall, 85.0% F1, 90.7% coverage, and 87.6% semantic mIoU, outperforming previous learning-based methods in both instance detection and mask completeness. Zero-shot evaluation on independent sites further demonstrates strong cross-domain generalization.

16.
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.

17.
arXiv (CS.AI) 2026-06-12

The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements

arXiv:2606.12797v1 Announce Type: new Abstract: Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly deployed in public-facing domains, including government services, healthcare triage, and financial advising. We ask whether the frameworks used to build these systems provide architectural-level structural safety guarantees. Applying six containment principles derived from a compositional model of agentic architectures, we audit three dominant frameworks (LangChain, AutoGPT, and OpenAI Agents SDK) and find no native compliance in any of them. Memory integrity, a defense against one of the most prevalent vulnerability classes, is not observed in any of the three evaluated frameworks. We validate these findings empirically: in a simulated government benefits agent built on LangChain, a single memory-poisoning write induces persistent targeted corruption across all tested seeds and backends, increasing the wrongful denial rate for targeted applicants to 88.9%. Under a complex five-factor policy, the same attack preserves aggregate accuracy while increasing targeted wrongful denials by 3.5x, rendering the corruption difficult to detect through standard monitoring. We then introduce two lightweight containment mechanisms: a memory integrity validator and a policy gate, which eliminate both attack vectors with sub-millisecond overhead (

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

Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning

arXiv:2606.14970v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data. A major obstacle in large-scale fine-tuning is the memory overhead of backpropagation, which requires storing activations, gradients, and optimizer states. Zeroth-order (ZO) optimization offers a memory-efficient alternative, but its performance is highly sensitive to the stepsize and smoothing parameter, often requiring costly task-specific tuning. Parameter-free (PF) optimization addresses this issue by adapting algorithmic parameters without prior knowledge of problem-dependent constants. Moreover, large-scale fine-tuning can benefit from geometry-aware updates that account for the heterogeneous structure of parameter blocks, which can be modeled through methods that exploit linear minimization oracle (LMO). In this work, we study PF adaptation for LMO-based ZO optimization and introduce $\texttt{AdaNAGED}$, a method that unifies gradient-free training, adaptive tuning, and non-Euclidean update geometry. We establish convergence guarantees and validate the method on large-scale LLM fine-tuning task with $\texttt{OPT}-1.3\mathrm{B}$ model.

19.
arXiv (CS.CV) 2026-06-18

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning. Instead, OneCanvas aggregates patch features from all views onto a single equirectangular panoramic canvas. Namely, each patch is unprojected to a 3D world coordinate using its depth and camera pose, then placed on the canvas at the continuous longitude and latitude of that point as seen from the canvas origin, with no rasterization or aggregation across overlapping views. A 3D position embedding of the patch's metric coordinates is added to its feature, restoring the depth lost when collapsing the world position to an angular canvas coordinate. Patches from all frames thus share one spatial coordinate system with no fusion or major architectural modifications of the backbone. The pretrained VLM consumes this representation as if it were an ordinary image. Because the canvas can be centered on any pose of interest, the same representation directly supports situated reasoning from a specific viewpoint, a common requirement in robotics and embodied AI. Thanks to this representation, we can also introduce a spatial pretraining curriculum: by procedurally placing patch features of objects, drawn from real images, at chosen 3D world positions on an otherwise empty canvas, we generate on-the-fly supervision spanning a broad range of spatial reasoning tasks, with answer distributions controlled to reduce spatial reasoning shortcuts. OneCanvas achieves state-of-the-art accuracy on SQA3D and VSI-Bench, and generalizes to out-of-distribution data on SPBench, using an order of magnitude less training compute than the strongest competing methods.

20.
arXiv (CS.CL) 2026-06-12

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory. Experiments show that current agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard benchmarks such as GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling evolution in both evaluation and memory for reliable agent deployment.

21.
Nature (Science) 2026-06-17

Towards autonomous medical artificial intelligence agents

作者:

Large language models (LLMs) show great potential for clinical decision-making, yet most applications remain narrow, task-specific chat tools rather than systems integrated into clinical workflows1,2. However, building physician copilots will require models that operate within the electronic health record (EHR), with governed access to patient data and the ability to initiate permitted EHR actions within defined safety constraints. Yet it remains unproven whether such a system can manage patient cases with physician-level performance. Here we show that MIRA (Medical Intelligence for Reasoning and Action), an autonomous artificial intelligence agent operating in a sandboxed EHR environment, can navigate a large clinical action space to obtain patient histories; order and interpret laboratory, imaging and microbiology tests; generate differential diagnoses; and formulate treatment plans such as prescribing medications, scheduling surgical procedures and planning admissions. In simulations on real patient cases spanning multiple diagnoses, MIRA outperformed physicians in diagnostic accuracy and made guideline-concordant, medication-safe and appropriate admission decisions. Compared with previous LLM applications that addressed isolated subtasks or provided free-text advice, these results suggest that an EHR-integrated artificial intelligence agent can turn clinical intent into structured, actionable EHR operations, possibly making it a more effective decision-support partner for physicians. Further work is needed to establish generalization, safety and governance through prospective, real-world studies. A large language model artificial intelligence agent operating in a sandboxed electronic health record system can autonomously&nbsp;take patient histories, order tests, interpret findings, diagnose conditions and propose treatments, outperforming experienced clinicians while adhering to safety standards and clinical guidelines.

22.
medRxiv (Medicine) 2026-06-15

Long-read sequencing enables high-accuracy mitochondrial heteroplasmy detection in Parkinson's disease

Background: Low-frequency heteroplasmic mitochondrial DNA (mtDNA) variants are associated with aging and neurological diseases, including Parkinson's disease (PD). Targeted deep mtDNA sequencing using PacBio HiFi long reads has the potential to resolve heteroplasmy across the full mitochondrial genome with high accuracy. Methods: To validate Vega PacBio sequencing for detecting mtDNA heteroplasmy, we analyzed four predefined mixtures of two mtDNA haplotypes. We generated a single long-range PCR amplicon covering the entire mitochondrial genome. These amplicons were mixed at predefined ratios (minor mixture haplotype component: 5%, 2%, 1%, and 0.1%). Variant calling was performed using Mutserve2, and accuracy was assessed by calculating the F1 score from comparisons between expected and detected variants. Full-length mtDNA PacBio sequencing was applied to investigate heteroplasmy across fibroblast passages derived from five LRRK2 p.Gly2019Ser variant carriers (n=3 affected with PD and n=2 unaffected carriers). Changes in mtDNA heteroplasmy level and variant load were assessed longitudinally using a linear mixed model. Results: The single-amplicon approach enabled full-length haplotype resolution without amplification bias associated with overlapping PCR strategies. The F1 score of the predefined mixtures was 1.0 for heteroplasmy levels between 5% and 1% and remained high (0.91) at 0.1%. We detected n=10/62 variants discordant with the Illumina reference at the 0.1% mixture, but sensitivity remained very high at 1.00 in that mixture. Detected minor variants closely matched expected heteroplasmy levels, with average variant levels of 0.057 (5%), 0.022 (2%), 0.011 (1%), and 0.001 (0.1%). Across twelve fibroblast passages, we observed fewer mtDNA heteroplasmic variants ({beta}=-3.2, p=0.026). Increased heteroplasmic variant load over time was also associated with older age ({beta}=1.50, p=0.001) and PD affection status ({beta}=5.0, p=1.0 x 10-4) in LRRK2 variant carriers. Notably, we observed distinct patterns of heteroplasmic variants that either increased or decreased in heteroplasmy level across passages. Conclusion: PacBio HiFi sequencing, combined with a single-amplicon strategy, enables accurate full-length mtDNA heteroplasmy detection and longitudinal analysis, providing a valuable tool for studying mitochondrial variation and dynamics in disease.

23.
arXiv (CS.CL) 2026-06-18

Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads

While large language models (LLMs) have become highly capable, they remain prone to factual inaccuracies, commonly referred to as "hallucinations." Uncertainty quantification (UQ) offers a promising way to mitigate this issue, but most existing methods are computationally intensive and/or require supervision. In this work, we propose Recurrent Attention-based Uncertainty Quantification (RAUQ), an unsupervised and efficient framework for identifying hallucinations. The method leverages an observation about transformer attention behavior: when incorrect information is generated, certain "uncertainty-aware" attention heads tend to reduce their focus on preceding tokens. RAUQ automatically detects these attention heads and combines their activation patterns with token-level confidence measures in a recurrent scheme, producing a sequence-level uncertainty estimate in just a single forward pass. Through experiments on twelve datasets spanning question answering, summarization, and translation across nine different LLMs, we show that RAUQ consistently outperforms state-of-the-art UQ baselines. Importantly, it incurs minimal overhead, requiring less than 1\% additional computation. Since it requires neither labeled data nor extensive parameter tuning, RAUQ serves as a lightweight, plug-and-play solution for real-time hallucination detection in white-box LLMs.

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

SUP-MCRL: Subject-aware Unified Pseudo-feature Coded Multimodal Contrastive Representation Learning for EEG Visual Decoding

Non-invasive brain-computer interfaces suffer severe fidelity degradation in neural visual decoding when generalizing to natural visual experiences. Conventional multimodal contrastive representation learning solely optimizes geometric distance alignment, neglecting semantic consistency and subject selectivity, causing spurious zero-shot alignment. We propose SUP-MCRL, a unified framework integrating three collaborative mechanisms: (1) Semantic-entity Aware Visual Encoder (SAVE), learning spatial attention to extract semantic content without pre-trained saliency models; (2 Unified EEG Enhancer (UEE), employing multi-scale atrous convolutions and inter-band attention for adaptive cross-subject robustness; and (3) Prototype-based Progressive Augmenter (PPA), maintaining an EMA-updated pseudo-feature pool to prevent representation collapse. Zero-shot experiments on THINGS-EEG achieve 66.0%/91.9% (Top-1/Top-5) intra-subject and 24.0%/52.9% LOSO accuracy, surpassing state-of-the-art methods. Code is available at https://github.com/NZWANG/SUP-MCRL.

25.
arXiv (CS.AI) 2026-06-18

Correcting Sensor-Induced Distribution Drift with Wasserstein Adversarial Learning

arXiv:2606.18561v1 Announce Type: cross Abstract: The quality of recorded data depends on the stability of the sensor system that acquires it. Sensor motion and aging can degrade the performance and stability of downstream data-driven methods. We present a Wasserstein-GAN-inspired approach for unsupervised inference of physically interpretable transformation parameters that map a changed detector response distribution back to a nominal reference distribution. In contrast to standard generative modeling, the generator is used as a learnable calibration transformation whose trainable weights represent the sought parameters, while the critic provides a distributional distance signal via the Wasserstein objective. We validate the approach on a tracking-detector toy model with controlled layer shifts and demonstrate its application on high-granularity Geant4-simulated calorimeter data with cell-wise aging effects. The method recovers aging coefficients for individual cells with correlation to ground truth and improves agreement between calibrated and reference energy-sum distributions, while exhibiting the expected degradation at increasing channel-to-channel noise levels. These results indicate that adversarial distribution matching can serve as a data-driven component of calibration strategies in settings where direct labels for degradation parameters are unavailable.