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.
medRxiv (Medicine) 2026-06-22

Age-related changes in acoustic cue use for speech-in-speech perception

Acoustic cues such as pitch and spatial location allow listeners to attend to a target speaker and ignore competing talkers, aiding speech recognition in background noise. Diminished ability to utilize acoustic cues for speech stream segregation may thus contribute to older adults' challenges hearing in noise. Adults aged 18-74 completed a speech-in-speech identification task with three conditions containing 1) only pitch cues (fundamental frequency), 2) only spatial cues (interaural time differences; ITDs), and 3) both pitch and spatial cues for segregating a target talker from competing talkers. Hearing thresholds at standard and extended high frequencies (EHFs), auditory brainstem responses (ABRs), and digit span scores were acquired to examine the influence of sensory and cognitive factors on use of each acoustic cue for speech-in-speech recognition. Significant differences were observed between cue condition scores indicating that use of the available cue(s) drove performance. ABR metrics were not a significant predictor but digit span scores significantly predicted scores on all three cue conditions. Working memory abilities therefore set a baseline for participants' speech-in-speech recognition regardless of the acoustic content. Hearing thresholds at standard frequencies significantly predicted scores on the Pitch condition. EHF hearing thresholds better predicted Spatial and Both Cue condition performance, suggesting that EHF thresholds represent auditory processing important for coding ITDs. Age group analysis revealed that older adults (aged 40+) performed significantly more poorly on all cue conditions of the speech-in-speech recognition task relative to younger adults. Age-related changes in auditory sensory processing may therefore impair older adults' speech-in-noise perception by reducing their ability to use acoustic cues for segregating target and competing speech.

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

Agentic Software: How AI Agents Are Restructuring the Software Paradigm

作者:

arXiv:2606.05608v2 Announce Type: replace-cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents – systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource – constitutes a fundamental restructuring of what software is, not an incremental tool improvement. We formalize the distinction between traditional deterministic software and agentic software: in the former, code is the carrier of pre-written decision logic; in the latter, the agent itself is the software, and its decision logic is generated at runtime. We trace the historical arc from licensed software to SaaS to Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users – with the agentic shift transferring not just operational complexity but decision-making complexity itself. We introduce Agentic Engineering as an expansion of the software engineering discipline into a new paradigm, distinct in its core object of study (agent systems rather than static source code), its control model (LLM-driven rather than human-predefined), and its human role (intent architect rather than code author). Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.

03.
arXiv (CS.CV) 2026-06-12

SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images

Vision-language models (VLMs) are increasingly used to detect whether AI-generated images contain visible artifacts, yet their ability to analyze such artifacts remains poorly understood. A correct image-level decision can still hide important failures: a model may correctly flag an artifact while relying on the wrong visual cue, selecting the wrong region, or describing a defect that the image does not support. To evaluate these behaviors directly, we introduce SalArt-VQA, a diagnostic benchmark for fine-grained SALient ARTifact understanding in AI-generated images. SalArt-VQA contains 950 images and 3,681 human-authored multiple-choice questions spanning artifact images, matched real reference images, and paired generated reference images. Four aligned question types evaluate presence detection, semantic localization, spatial grounding, and evidence-grounded defect identification, while the reference splits test calibration and abstention when the annotated defect is absent. Across 20 VLMs, SalArt-VQA reveals failures that image-level detection accuracy hides: the strongest model reaches 99.37% detection recall on artifact images but answers all four artifact-side questions correctly on only 53.26% of images. Comparing artifact images with artifact-free references reveals a sensitivity-calibration tradeoff: sensitive models often make unsupported artifact claims, while conservative models avoid false alarms largely by missing real artifacts. These results show that high artifact detection accuracy alone does not imply grounded artifact understanding. SalArt-VQA exposes these hidden failure modes and provides a fine-grained evaluation of whether VLM artifact claims are supported by local visual evidence.

04.
medRxiv (Medicine) 2026-06-17

Efficacy of a Gamified Digital Platform for Substance Use Education and Overdose Prevention Among College Students: a Pilot and Feasibility Study

Background: For US young adults aged 18-25 in the 2018-2024 period, fentanyl was involved in 78.2% of the 44,020 unintentional or undetermined-intent overdose deaths, most often co-involving stimulants and other non-opioid substances. While fatal overdose rates in this age group have fallen to their lowest recorded level, emergency medical services-attended non-fatal overdose events have reached record highs, shifting the decisive variable toward bystander recognition and response. College students report near-universal alcohol education but minimal education on the substances actually driving overdose mortality. Methods: We conducted a single-group pre-post evaluation of the DopaGE Portal, a gamified, mastery-based digital platform covering cocaine, MDMA, benzodiazepines, and opioid overdose response, deployed at a public university (UNL) and a multi-campus volunteer network (TACO). Paired pre/post surveys (N=42) measured self-efficacy (7 items; primary), behavioral intentions, risk perception, and knowledge/attitudes on 5-point scales, plus four factual knowledge questions. Paired t-tests, exact McNemar tests, and Benjamini-Hochberg correction across eight primary tests were applied. Institutional naloxone distribution at UNL was tracked as an ecological behavioral outcome. A mandated high-school cohort (N=94) provided supplementary acceptability data. Results: Self-efficacy increased from 2.82 to 4.46 (d=2.00, 95% CI 1.46-2.55; adjusted p

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

APT: Atomic Physical Transitions for Causal Video-Language Understanding

Physical events are not understood by their names alone, but by the causal state changes that compose them. A clip-level label such as "bounce" can be correct while hiding the process that makes the event physically valid, from support loss and contact onset to rebound and settling. To make this hidden process explicit, we introduce Atomic Physical Transitions (APTs): minimal, temporally localized state changes that bind a visible cue to an active physical mechanism and before/after dynamical regimes. An APT chain represents a video as an ordered causal transition sequence rather than a single aggregate event label: event labels tell what happened; APT chains explain why it happened. To make APTs learnable by VLMs, we construct mixed-source APT data from human annotations and simulator ground truth, covering 14 transition types across contact, gravity, friction, and rotation/stability, with 27,303 timed instances over 1,246 trials. Using this data, we find that current VLMs miss transition-level physics, with zero-shot recall at most 14% and errors dominated by missed transitions. Direct fine-tuning on APT chains improves transition detection but causes event-level forgetting, indicating that the model learns a specialized answer format rather than a reusable physical representation. We therefore propose APT-Tune, a parameter-efficient recipe that teaches VLMs to use causal transitions without forgetting how to answer video questions. It combines image-pad-aware supervision, format-conditional co-training, and mechanism-conditioned domain-to-type decoding to make APT learning format-robust and physically grounded. With only 11 M LoRA parameters on Qwen3-VL-2B, APT-Tune substantially improves APT recall while also improving event-level video transfer. These results show that APTs are not a new answer format, but a human-aligned causal supervision signal for physical video understanding.

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

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and reward them independently. This optimizes for pass@1 performance and prioritizes the strength of isolated samples at the expense of the diversity and collective utility of sets of samples. This under-utilizes the sampling capacity, limiting exploration and eventual improvement on harder examples. As a fix, we propose Pass-at-k Policy Optimization (PKPO), a transformation on the final rewards which leads to direct optimization of pass@k performance, thus optimizing for sets of samples that maximize reward when considered jointly. Our contribution is to derive novel low variance unbiased estimators for pass@k and its gradient, in both the binary and continuous reward settings. We show optimization with our estimators reduces to standard RL with rewards that have been jointly transformed by a stable and efficient transformation function. While previous efforts are restricted to k=n, ours is the first to enable robust optimization of pass@k for any arbitrary k

07.
medRxiv (Medicine) 2026-06-16

The Target48 Neurodegeneration Panel: A Novel Tool for Profiling Protein Signatures in Neurodegenerative Disorders

Introduction: Novel tools for absolute quantification of established and emerging fluid neuro-biomarkers are required to advance diagnostic studies and improve biological insights. Methods: We conducted an extensive analytical and clinical validation of the Olink Target 48 Neurodegeneration panel (T48 Neuropanel) in 352 paired CSF and plasma samples from cognitively unimpaired controls (CU), Alzheimer dementia (AD), frontotemporal dementia (FTD), and dementia with Lewy bodies (DLB), n=44 per group. Comparisons with benchmark assays were performed. Results: Good detectability (CSF: 31 out of 42 assays; plasma: 38 out of 42 assays) and technical performance was observed. Benchmark assays showed good correlations, supporting method transformation formulas. Next to emerging biomarkers (MMP10, ITGB2), discriminative performance was excellent in AD: CSF pTau217: AUC=1; FTD: plasma NfL: AUC=0.952; and DLB: CSF DDC: AUC=0.901. Discussion: This analytical and clinical validation of the T48 Neuropanel highlights initial cut-offs and emerging biomarkers to aid clinical studies for the diagnosis, prognosis, and monitoring of neurodegenerative diseases. Highlights: The T48 Neuropanel shows robust analytical performance, with high detectability across both plasma and CSF matrices. The T48 Neuropanel validates established (i.e., pTau217, Abeta42, NfL, and GFAP) and emerging biomarkers (i.e., DDC, MMP10, ITGB2, ITGAM, NPTX2, NPTXR, SMOC1, sTREM1, and sTREM2) in CSF and plasma. CSF NfL, GFAP, ITGB2, and ITGAM and plasma GFAP were dysregulated across AD, FTD, and DLB dementias. -The multiplex design of the T48 Neuropanel enables rich biological interpretation by simultaneously quantifying established and emerging neurodegeneration biomarkers. Importantly, the inclusion of absolute quantification facilitates the establishment of cut-offs, supporting its potential for clinical translation.

08.
arXiv (CS.LG) 2026-06-15

Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens

arXiv:2606.14620v1 Announce Type: new Abstract: Open diffusion language models are marketed as parallel, non-autoregressive decoders, yet the order in which a shipped checkpoint actually commits its tokens is almost never measured. We instrument DiffusionGemma 26B, a masked discrete-diffusion mixture-of-experts model built on Gemma 4, hooking its sampler's accept step to record which canvas positions commit, when, and at what confidence. Across a 686-prompt, six-regime probe suite we find that its decoding is neither parallel nor block-autoregressive: it follows a partial left-to-right commit bias whose apparent strength depends almost entirely on the granularity at which you look. Order is weak token by token and strengthens smoothly as the analysis is coarsened, so the model's "block size" turns out to be an artifact of the measuring ruler rather than the architecture. The model commits in large simultaneous batches, leaving much of the within-batch order genuinely undefined rather than merely unobserved. The behaviour is regime-dependent: structured JSON is committed in essentially arbitrary order, and a position's commit confidence tracks correctness on mathematical reasoning but carries no signal on factual recall. Commitment is aggressive, finishing in a short late burst well inside the step budget, while task accuracy matches the model's autoregressive Gemma-4 sibling. Beyond these findings, our central contribution is methodological: measuring decoding order honestly demands handling trailing-EOS padding, within-regime confounding, commit non-monotonicity, block-size sensitivity, and large commit-batch ties, each of which can otherwise manufacture a decoding-order result that is not really there.

09.
medRxiv (Medicine) 2026-06-11

A Global Health Quality Improvement Project: Enhancing Cervical Cancer Awareness and screening in Nigeria

Background Cervical cancer remains a significant global public health challenge, ranking as the fourth most common cancer among women worldwide. According to The World Health Organization (WHO) 604,000 women were diagnosed with cervical cancer globally in 2020, with over 342,000 deaths amongst this group [1]. Despite its high mortality, cervical cancer is largely preventable through early detection and vaccination against human papillomavirus (HPV), which causes nearly all cases of cervical cancer [1,2] In Nigeria, it is the second most common cancer among women in Nigeria and a leading cause of cancer-related deaths, with low screening rates exacerbating late diagnoses and poor outcomes [1]. Despite global commitments to elimination with Pap smear screening and HPV vaccination, less than 10% of women in Nigeria have undergone screening due to misconceptions, stigma, and limited awareness. Educational interventions may improve awareness and promote screening behaviors. This global health quality improvement (QI) project aimed to enhance cervical cancer awareness and increase Pap smear uptake at the Central Bank of Nigeria (CBN) Clinic in Abuja, Nigeria. Methods In November 2024, we conducted a health education intervention at the Central Bank of Nigeria (CBN) through a structured educational session for male and female CBN staff members. The session focused on cervical cancer prevention, risk factors, and screening guidelines. Additionally, cervical cancer awareness was raised via email, social media, and electronic bulletin board. Participants completed pre and post-interventions surveys assessing cervical cancer knowledge across 10 key items and demographic characteristics. Pap smear uptake was assessed using the CBN clinic records for three months before and after the intervention. Institutional approval was obtained from CBN and external institutional review board approval was not required. Results 188 participants attended the health education session with 124 survey responses (70 pre-event, 54 post-event). Participants were mostly women aged 30-39. Post-intervention, eight of ten survey questions showed improved knowledge, with five demonstrating statistically significant gains: understanding Pap smear frequency (p

10.
Nature (Science) 2026-06-10

Light slows down carbon nanotubes in water

Water-suspended carbon nanotubes move more slowly in green light, suggesting that excited electrons in the tubes couple to the water through ‘quantum friction’. Water-suspended carbon nanotubes move more slowly in green light, suggesting that excited electrons in the tubes couple to the water through ‘quantum friction’.

11.
arXiv (CS.CV) 2026-06-11

Time-Conditioned and Multi-Time Survival Prediction from 2D PET/CT Projections in Lung Cancer

Accurate prediction of overall survival (OS) from positron emission tomography/computed tomography (PET/CT) can support personalized treatment and follow-up strategies in oncology. However, the impact of temporal modeling on imaging-based survival prediction remains insufficiently explored. We investigate how different temporal formulations influence survival prediction by developing two complementary approaches: Attention-guided Time-Conditioned Survival (ATCS) and Multi-Time Survival (MTS). We retrospectively analyzed pre-treatment PET/CT images from 848 patients with non-small cell lung cancer (NSCLC), including 556 for model development and 292 for held-out testing. A previously proposed Time-Conditioned Survival (TCS) model was used as a baseline. Models were trained using 5-fold cross-validation and evaluated on the test set using time-dependent area under the curve (AUC) at 6-month intervals from 0.5 to 5 years. Both ATCS and MTS outperformed the baseline TCS model, achieving mean AUCs of 0.794 and 0.793, respectively, compared to 0.767. ATCS performed better at earlier time points (0.5-3 years), whereas MTS performed better at later intervals (3.5-5 years). Combining tumor-specific and tissue-wise PET/CT features improved performance over either input alone. Finer temporal discretization improved short-term prediction, while coarser intervals provided more stable long-term estimates. These findings demonstrate that temporal modeling and input design influence PET/CT-based survival prediction. The proposed approaches enable time-specific survival estimation from pre-treatment imaging and may support improved risk stratification and clinical decision-making.

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

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, but provide only sparse supervision during training. Distillation provides dense token-level supervision, typically obtained from an external teacher or using high-quality demonstrations. Collecting such supervision can be costly or unavailable. We propose Self-Distillation Zero (SD-Zero), a method that is substantially more training sample-efficient than RL and does not require an external teacher or high-quality demonstrations. SD-Zero trains a single model to play two roles: a Generator, which produces an initial response, and a Reviser, which conditions on that response and its binary reward to produce an improved response. We then perform on-policy self-distillation to distill the reviser into the generator, using the reviser's token distributions conditioned on the generator's response and its reward as supervision. In effect, SD-Zero trains the model to transform binary rewards into dense token-level self-supervision. On math and code reasoning benchmarks with Qwen3-4B-Instruct and Olmo-3-7B-Instruct, SD-Zero improves performance by at least 10% over the base models and outperforms strong baselines, including Rejection Fine-Tuning (RFT), GRPO, and Self-Distillation Fine-Tuning (SDFT), under the same question set and training sample budget. Extensive ablation studies show two novel characteristics of our proposed algorithm: (a) token-level self-localization, where the reviser can identify the key tokens that need to be revised in the generator's response based on reward, and (b) iterative self-evolution, where the improving ability to revise answers can be distilled back into generation performance with regular teacher synchronization. Code: https://github.com/princeton-pli/Self-Distillation-Zero.

13.
arXiv (CS.CL) 2026-06-17

Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Models

Understanding how humans collaborate and communicate in teams is essential for improving human-agent teaming and AI-assisted decision-making. However, relying solely on data from large-scale user studies is impractical due to logistical, ethical, and practical constraints, necessitating synthetic models of multiple diverse human behaviors. Recently, agents powered by Large Language Models (LLMs) have been shown to emulate human-like behavior in social settings. But, obtaining a large set of diverse behaviors requires manual effort in the form of designing prompts. On the other hand, Quality Diversity (QD) optimization has been shown to be capable of generating diverse Reinforcement Learning (RL) agent behavior. In this work, we combine QD optimization with LLM-powered agents to iteratively search for prompts that generate diverse team behavior in a long-horizon, multi-step collaborative environment. We first show, through a human-subjects experiment, that humans exhibit diverse coordination and communication behavior in this domain. We then present a series of experiments showing that our approach captures behaviors that are difficult to observe without large-scale data collection, and a follow-up user study to show that these generated behaviors are human-like. Our findings highlight the combination of QD and LLM-powered agents as an effective tool for studying teaming and communication strategies in multi-agent collaboration.

14.
arXiv (CS.LG) 2026-06-19

Meta Flow Maps enable scalable reward alignment

arXiv:2601.14430v2 Announce Type: replace-cross Abstract: Controlling generative models is computationally expensive. This is because optimal alignment with a reward function–whether via inference-time steering or fine-tuning–requires estimating the value function. This task demands access to the conditional posterior $p_{1|t}(x_1|x_t)$, the distribution of clean data $x_1$ consistent with an intermediate state $x_t$, a requirement that typically compels methods to resort to costly trajectory simulations. To address this bottleneck, we introduce Meta Flow Maps (MFMs), a framework extending consistency models and flow maps into the stochastic regime. MFMs are trained to perform stochastic one-step posterior sampling, generating arbitrarily many i.i.d. draws of clean data $x_1$ from any intermediate state. Crucially, these samples provide a differentiable reparametrization that unlocks efficient value function estimation. We leverage this capability to solve bottlenecks in both paradigms: enabling inference-time steering without inner rollouts, and facilitating unbiased, off-policy fine-tuning to general rewards. Empirically, our single-particle steered-MFM sampler outperforms a Best-of-1000 baseline on ImageNet across multiple rewards at a fraction of the compute.

15.
arXiv (CS.LG) 2026-06-16

Dual-Network PINNs for Optimal Control: A Reproducible Benchmark on the Mass-Spring-Damper System

arXiv:2606.15271v1 Announce Type: cross Abstract: This work presents a transparent and reproducible benchmark study of a direct dual-network Physics-Informed Neural Network (PINN) formulation for the optimal control of a mass-spring-damper system. The classical linear-quadratic optimal control problem is solved by two independent classical methods – Pontryagin's Minimum Principle with single shooting, and direct transcription through trapezoidal collocation – and recast as a constrained optimization problem solved by two feedforward neural networks: a state network whose boundary conditions are enforced exactly through a composite cubic-and-mask ansatz, and an unconstrained control network. The composite loss combines the physics residual at the collocation points with a trapezoidal approximation of the cost functional, weighted by a single scalar hyperparameter. On the benchmark considered, the PINN reproduces the classical optimal cost to four significant digits, satisfies the terminal state constraints exactly by construction, and produces pointwise state and control errors that fall within the spread of the two classical references. Training is approximately two orders of magnitude slower than classical shooting on this benchmark, which is honestly reported. The contribution is methodological clarity rather than methodological novelty: the formulation and the accompanying Google Colab implementation are intended to lower the barrier to entry for practitioners exploring PINN-based optimal control without prior exposure to adjoint methods or two-point boundary value problems.

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

Fi-Gaussian: Frequency-Aware Implicit Gaussian Splatting for Single Image Dehazing

Single image dehazing continues to be hindered by the loss of high-frequency details and the difficulty of accurate physical scattering modeling. To address these issues, we propose Fi-Gaussian, a frequency-aware implicit Gaussian splatting network for single image dehazing. Unlike explicit rendering methods that rely on 3D point clouds, our method employs implicit Gaussian splatting to adaptively model the underlying distribution of clear images as a continuous representation in 2D feature space. The core of the network is a frequency-aware implicit Gaussian splatting module, which decouples low-frequency structural information and high-frequency texture information in the frequency domain and then performs adaptive Gaussian aggregation with complex-valued weights to recover fine details. In addition, a physics-driven scattering renormalization mechanism is introduced to estimate the transmission map and atmospheric light under the guidance of implicit Gaussian priors. Extensive experiments on multiple benchmark datasets demonstrate that Fi-Gaussian achieves state-of-the-art quantitative performance and produces visually superior dehazed results, validating the effectiveness of implicit Gaussian splatting for low-level vision tasks.

17.
arXiv (CS.CV) 2026-06-16

Effective and Low-cost Lane-based Map Localization for Vehicle-Centric Route Generation

Driver-centric route representation plays a vital role in intuitive driving guidance systems. This paper presents OLRA, a low-cost, map-localization-based framework that derives driver-view-aligned routes by matching map-based navigation routes with camera-detected lane markings. This alignment process mutually enhances vehicle localization accuracy and visual route consistency. To bridge the evaluation gap across different paradigms, we introduce practical route evaluation metrics and benchmark OLRA against OpenPilot, a representative direct-generation approach. Experimental results on the nuScenes dataset demonstrate that OLRA outperforms OpenPilot in complex road segments and in route estimation at distance beyond 20 meters, achieving lower overall Euclidean error. This study is expected to promote future research in low-cost, maplocalization-based route generation methods.

18.
arXiv (CS.LG) 2026-06-17

The Morse Transform for Discrete Shape Analysis

arXiv:2503.04507v2 Announce Type: replace-cross Abstract: The geometry of an object plays a vital role in modulating its interactions with the physical world. It nevertheless remains difficult to describe geometric information numerically for the purposes of statistical inference or classification tasks. Here, we introduce a new topological transform which leverages directional piecewise-linear Morse theory to quantify the geometry of an embedded object by cataloguing critical points across multiple height-functions. The output of this Morse transform records both the heights and the local topological type (peak, trough or saddle) of the critical points that characterise the underlying shape, retaining finer information than the Euler characteristic transform whilst naturally prioritising a shape's outermost regions. Crucially, this output can be further compressed into a rich but compact feature vector. We benchmark the Morse feature vector as a descriptor for ligand-based virtual screening (LBVS), which intrinsically depends on the shape of molecules. Under a common gradient-boosted tree classification pipeline, Morse descriptors achieve the highest mean AUROC when compared to other topological transform descriptors and to standard shape-based LBVS descriptors.

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

CARE: Controlling LLM-Generated Policies through Auditable Review of Evidence in Scientific Experimentation

arXiv:2606.14581v1 Announce Type: cross Abstract: Granting LLMs direct control over costly, irreversible scientific experiments leads to unsafe exploration and unstable performance, but discarding LLM creativity entirely sacrifices significant optimization potential. We introduce CARE (Controlling LLM-Generated Policies through Auditable Review of Evidence in Scientific Experimentation), an auditable controller for high-throughput experimentation (HTE) optimization that keeps a non-LLM incumbent optimizer as the default action path while using LLMs to revise challenger ranking policies. Before each outcome is revealed, a public-evidence intervention gate compares the challenger with the incumbent. It authorizes the challenger's selection only when the evidence available before selection supports the change, with the decision recorded in the audit log. CARE outperforms all other evaluated methods on Minerva/Olympus and ChemLex benchmarks, with final-best improving from 80.0 to 88.5 on Minerva/Olympus and from 83.9 to 92.1 on ChemLex, relative to the public incumbent. Our experiments indicate that LLM self-evolution is more reliable when it expands the proposal space under an auditable controller, rather than directly choosing experiments.

20.
arXiv (CS.AI) 2026-06-15

Generalized Discrete Diffusion with Self-Correction

arXiv:2603.02230v2 Announce Type: replace-cross Abstract: Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such approaches often suffer from limited generalization and may impair reasoning performance. GIDD pioneers pretraining-based self-correction via a multi-step BERT-style uniform-absorbing objective. However, GIDD relies on a continuous interpolation-based pipeline with opaque interactions between uniform transitions and absorbing masks, which complicates hyperparameter tuning and hinders practical performance. In this work, we propose a Self-Correcting Discrete Diffusion (SCDD) model to reformulate pretrained self-correction with explicit state transitions and learn directly in discrete time. Our framework also simplifies the training noise schedule, eliminates a redundant remasking step, and relies exclusively on uniform transitions to learn self-correction. Experiments at the GPT-2 scale demonstrate that our method enables more efficient parallel decoding while preserving generation quality.

21.
arXiv (CS.LG) 2026-06-15

DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation

arXiv:2606.14192v1 Announce Type: new Abstract: Auto-bidding is a core component of real-time advertising systems, where decisions must optimize long-term performance under budget and cost constraints, while online exploration is prohibitively risky. Offline reinforcement learning and, more recently, Transformer-based sequence modeling have shown promise for learning bidding policies from logged data, but their unimodal and purely parametric formulations often collapse multiple effective bidding strategies into suboptimal averaged actions and perform unreliably under sparse or long-tail traffic. To mitigate these limitations, we propose DRIVE (Distributional and Retrieval-Augmented Bidding with Value Evaluation), a unified Transformer-based framework that decouples candidate action generation from decision making for offline auto-bidding. DRIVE combines distributional action modeling, retrieval-augmented candidate generation from high-quality historical decisions, and value-based evaluation to select the most promising bid at inference time. Extensive experiments on AuctionNet and additional offline reinforcement learning benchmarks demonstrate that DRIVE consistently improves bidding performance and generalizes well across multiple Transformer-based methods.

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

Assessment of Personality Dimensions Across Situations in Dyadic Role-Play Scenarios

arXiv:2507.19137v3 Announce Type: replace-cross Abstract: Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in automatic personality perception (APP), which aims to predict an individual's perceived personality traits. Previous studies in APP have treated personalities as static traits, independent of context. However, perceived personalities can vary by context and situation as shown in psychological research. In this study, we investigate the relationship between conversational speech and perceived personality for participants engaged in two work situations (a neutral interview and a stressful client interaction). Our key findings are: 1) perceived personalities differ significantly across interactions, 2) loudness, sound level, and spectral flux features are indicative of perceived extraversion, agreeableness, conscientiousness, and openness in neutral interactions, while neuroticism correlates with these features in stressful contexts, 3) handcrafted acoustic features and non-verbal features outperform speaker embeddings in inference of perceived personality, and 4) stressful interactions are more predictive of neuroticism, aligning with existing psychological research.

23.
arXiv (CS.AI) 2026-06-17

Blueprint First, Model Second: A Framework for Deterministic LLM Workflow

arXiv:2508.02721v2 Announce Type: replace-cross Abstract: While powerful, the inherent non-determinism of large language model (LLM) agents limits their application in structured operational environments where procedural fidelity and predictable execution are strict requirements. This limitation stems from current architectures that conflate probabilistic, high-level planning with low-level action execution within a single generative process. To address this, we introduce the \textsc{Source Code Agent} framework, a new paradigm built on the ``Blueprint First, Model Second'' philosophy that decouples workflow logic from the generative model. An expert-defined operational procedure is first codified into a source code-based Execution Blueprint, which is then executed by a deterministic engine. The LLM is strategically invoked as a specialized tool to handle bounded, complex sub-tasks within the workflow, but never to decide the workflow's path. We evaluate on the TravelPlanner benchmark for constraint-aware travel planning. The \textsc{Source Code Agent} achieves a 35.56\% final pass rate, a 97.6\% improvement over the state-of-the-art ATLAS baseline (18.00\%) on the same Claude-Sonnet-4 backbone. Critically, it reduces constraint violations by 96.0\% (11 vs 275) while improving execution efficiency by 27.1\% (10.2$\pm$0.7 steps vs 14.0). Two production incident-diagnosis deployments and additional results on ScienceWorld and ALFWorld confirm that the architecture transfers beyond travel planning to procedurally well-defined, constraint-intensive workflows. Our work enables the verifiable and reliable deployment of autonomous agents in applications governed by strict procedural logic.

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

Finite-Time Convergence of Distributionally Robust Q-Learning with Linear Function Approximation

arXiv:2510.01721v3 Announce Type: replace Abstract: Distributionally robust reinforcement learning (DRRL) seeks policies that perform well when the deployment transition model differs from the nominal model generating the data. Most finite-sample guarantees for DRRL are tabular, model-based, rely on generative access, or obtain function-approximation guarantees only under additional structure, such as linear-transition models or restrictive discount-factor conditions. We study discounted model-free robust Q-learning under an $(s,a)$-rectangular chi-square uncertainty set, with linear approximation of the robust Q-function, using only a single Markovian trajectory from an unknown nominal model. Our algorithm combines a target-network outer loop with a dual function-approximation scheme for the chi-square robust Bellman update. The dual procedure uses moment-tracking critics, suffix averaging, a fresh-evaluation stage for the variance-like moment, and a tunable smoothing parameter to have a Lipschitz-continuous chi-square dual gradient. We prove a finite-time convergence bound to the optimal robust Q-function up to approximation error, without imposing a small-discount-factor assumption. Our results help close a gap between the empirical use of robust RL algorithms and the non-asymptotic guarantees available for their non-robust counterparts.

25.
arXiv (CS.AI) 2026-06-16

MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency

arXiv:2606.15148v1 Announce Type: cross Abstract: Inverse kinematics (IK) remains a critical bottleneck for real-time robot manipulation. Classical numerical solvers achieve high geometric precision but often suffer from discontinuous branch switching and unstable behavior near kinematic singularities during closed-loop deployment. Meanwhile, learned IK approaches frequently struggle to balance spatial accuracy, motion smoothness, and real-time efficiency, particularly when trained on noisy human teleoperation data. We present MimicIK, a real-time generative inverse kinematics framework that learns smooth and robust joint-space motion priors from teleoperation demonstrations through conditional flow matching. Given the current joint configuration and a target end-effector pose, MimicIK predicts continuous delta-joint commands using an efficient two-step iterative refinement process based on a Minimal Iterative Policy (MIP) backbone. To enforce physical consistency, we further introduce an FK consistency loss, a differentiable forward-kinematics regularization that penalizes task-space deviations from the target pose during training. We evaluate MimicIK on a real-world 6-DOF robot dataset containing 8,848 teleoperation demonstrations. MimicIK achieves a mean position error of 4.65 mm, a 10 mm success rate of 92.01\%, and a trajectory spike rate of only 7.99\%. Compared with a UNet diffusion baseline, our method improves both spatial accuracy and motion smoothness while reducing inference latency from 21.66 ms to 6.74 ms. Furthermore, unlike deterministic MLP baselines that catastrophically diverge under out-of-distribution deployment, MimicIK remains stable near singular configurations and enables robust 20 Hz real-time control on deployment hardware.