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.CV) 2026-06-15

RT-VLA: Real-Time Vision-Language-Action Models via Knowledge Distillation

Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction. However, their large vision-language backbones and reasoning modules introduce substantial inference latency and thereby prevent their deployment in the unforgiving reality of the road networks. We propose RT-VLA, a lightweight, distilled VLA model that transfers the driving and reasoning capabilities of the state-of-the-art SimLingo model into a compact student through multi-level supervised distillation. RT-VLA preserves language-based reasoning and supports post-hoc explanation through offline language analysis of safety-critical driving moments without adding latency to real-time control. Compared to the SimLingo teacher, RT-VLA maintains competitive closed-loop driving and language reasoning performance while reducing inference time by 44.8X in vision-only mode and 7.9X in vision+language mode. These results suggest that supervised distillation is a practical approach for building real-time, explainable VLA-style autonomous driving models.

02.
arXiv (CS.CL) 2026-06-15

ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion

Fixed-cardinality retrieval injects a constant top-K chunks into the generator regardless of query complexity, causing over-retrieval for narrow queries and under-retrieval for compositional ones. We describe ScoreGate, a lightweight score-space decision mechanism that controls retrieval cardinality at inference time using two scores already produced by the standard pipeline: bi-encoder similarity s_i and cross-encoder reranker score r_i, with no additional model inference calls required. Its core insight is that cross-encoder affirmation can rescue semantically relevant chunks that bi-encoder retrieval ranks poorly due to vocabulary mismatch – a failure mode unaddressed by fixed-K or single-score thresholding. On MS MARCO (200 dev queries), ScoreGate achieves MRR@10 = 0.401 with 35% fewer retained chunks than Standard Top-K. On an internal benchmark (n=300, Fleiss' kappa=0.87), ScoreGate observed zero false positives (95% CI [96.4%, 100%]) at 97.77-99.34% recall, with 34.8% fewer tokens per query and only 31ms added latency. Results on both MS MARCO and real-world production traffic suggest that adaptive retrieval cardinality can improve retrieval efficiency without degrading retrieval quality.

03.
arXiv (CS.LG) 2026-06-24

Verifiable Foundation Models for Robot Safety

arXiv:2606.23754v1 Announce Type: cross Abstract: Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes these models opaque and difficult to analyze formally, rendering them intractable for existing verification tools. In this paper, we present FEARL (Foundation-Enabled Assured Robot Learning), a framework that addresses this tension through a modular architectural decomposition. FEARL separates the policy into a large Controller (C) responsible for high-dimensional perception and task reasoning, and a small Safety module (S) that receives low-dimensional observations from dedicated safety sensors together with a bounded context embedding from C and produces the final action. Since many robot safety requirements, such as collision avoidance and workspace boundary constraints, can be expressed over these safety sensor observations, formal verification can be applied to S rather than to the full foundation-model backbone. This makes formal analysis tractable with existing tools while preserving the Controller's expressive power for task reasoning. To show that the decomposed policy remains capable of solving diverse tasks, we evaluate FEARL on three simulated robotic domains using multiple Controller backbones and training procedures, including pretrained off-the-shelf vision-language-action models. We further transfer the learned policy from one of our simulated tasks to a physical robot, suggesting that the low-dimensional safety interface supports practical sim-to-real transfer.

04.
arXiv (CS.LG) 2026-06-18

Geometric and Stochastic Analysis of Discontinuities in Sparse Mixture-of-Experts

arXiv:2606.19036v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (SMoE) architectures are now widely deployed in state-of-the-art language and vision models, where conditional routing allows scaling to very large networks. However, this very Top-$k$ expert selection that enables conditional routing also renders the SMoE map inherently discontinuous. In the vicinity of these discontinuity surfaces, even inputs that are arbitrarily close may activate substantially different sets of experts resulting in significantly different outputs. In this work we give a rigorous geometric and stochastic analysis of these discontinuities. We first classify them by order, determined by the number of tied experts at a switching event. Using measure-theoretic slicing arguments, we establish asymptotic volume estimates for the thickened discontinuity surfaces, showing that lower-order discontinuity sets dominate, whereas higher-order ones occupy a vanishingly small relative volume. Next, modeling random perturbations in the input space via a diffusion process, we prove that the path eventually encounter a discontinuity, and moreover that the first hit almost surely occurs on an order-1 discontinuity with explicit finite-time probability bounds. We further derive occupation-time bounds that quantify the duration the random path spend in the neighborhoods of each discontinuity order. These theoretical results imply that inputs are more likely to lie near lower order discontinuities. Motivated by this insight, we propose a simple smoothing mechanism that can be directly applied to existing SMoEs, softly incorporating experts near discontinuities; our analysis guarantees that the added computational overhead remains small while providing localized smoothing near discontinuities, and experiments across language and vision tasks show that smoothing not only enforces continuity of the SMoE map but also enhances empirical performance.

05.
arXiv (CS.CV) 2026-06-16

Post-Launch Capability Expansion of Vision-Language Models via Prompting for On-Orbit Spacecraft Inspection

Spaceborne inspection systems often deploy perception models prior to launch, after which updating model weights or expanding fixed label sets becomes operationally impractical. While supervised models can be integrated pre-flight, adding new semantic capabilities in orbit requires retraining and re-uploading parameters. We investigate whether prompt-driven vision–language models can enable post-launch semantic expansion, allowing new spacecraft components to be specified via natural-language prompts without modifying onboard weights. We evaluate zero-shot instance segmentation of spacecraft components under a strictly frozen, single-pass inference protocol on a test set of $129$ images of previously unseen satellites. Under fixed global thresholds and no post-processing, SAM3 achieves $0.385$ mAP@$0.5$ and $0.267$ mAP@$0.5{:}0.95$. Performance is strongly scale-dependent: large structural elements like spacecraft bodies ($0.639$ AP@$0.50$) and solar arrays ($0.598$ AP@$0.5$) localize reliably, while relatively small appendages like antennas ($0.221$ AP@$0.5$) and thrusters ($0.081$ AP@$0.5$) remain difficult. Prompt formulation influences performance, with structured prompts incorporating spatial and geometric descriptors yielding up to $82%$ improvement over short category-name prompts. The model operates within the memory and compute envelope of contemporary embedded GPUs, suggesting prompt-driven grounding can provide a practical mechanism for post-launch semantic extension of dominant spacecraft structures while highlighting limitations of zero-shot localization for fine-scale components under orbital domain shift.

06.
arXiv (CS.CV) 2026-06-25

What Does the Brain See? Multiview Neural Representations to Demystify the Brain-Visual Alignment

Zero-shot visual decoding from electroencephalography (EEG) aims to infer visual semantics from non-invasive neural recordings, but remains challenging due to the low signal-to-noise ratio, non-stationarity, and limited spatial resolution of EEG. Existing EEG-vision alignment methods often rely on holistic EEG embeddings, which can obscure the complementary temporal, spectral, and spatial structure underlying visual perception. We introduce a unified multiview EEG representation learning framework for aligning brain responses with visual semantic embeddings. Our method builds an EEG encoder that jointly models three complementary views: input-conditioned state-space temporal dynamics, learnable wavelet-based spectral decomposition for sample-adaptive frequency modeling, and attention-modulated graph learning for structured electrode interactions. The resulting multiview EEG embeddings are fused and aligned with pretrained visual representations in a shared semantic space using contrastive learning with EEG-specific regularization, enabling 200-way zero-shot visual classification. Experiments on THINGS-EEG benchmark show that our method achieves state-of-the-art performance, with 54.8% Top-1 and 85.6% Top-5 accuracy in the within-subject setting and 15.3% Top-1 and 45.4% Top-5 accuracy in the cross-subject setting. We further present the first systematic cross-session EEG-image decoding evaluation, achieving 40.8% Top-1 and 78.0% Top-5 accuracy. These results suggest that explicitly modeling multiview neural structure improves both semantic alignment and generalization in EEG-based visual decoding.

07.
arXiv (CS.AI) 2026-06-24

MyoInteract: A Framework for Fast Prototyping of Biomechanical HCI Tasks using Reinforcement Learning

arXiv:2602.15245v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL)-based biomechanical simulations have the potential to revolutionise HCI research and interaction design, but currently lack usability and interpretability. Using the Human Action Cycle as a design lens, we identify key limitations of biomechanical RL frameworks and develop MyoInteract, a novel framework for fast prototyping of biomechanical HCI tasks. MyoInteract allows designers to setup tasks, user models, and training parameters from an easy-to-use GUI within minutes. It trains and evaluates muscle-actuated simulated users within minutes, reducing training times by up to 98%. A workshop study with 12 interaction designers revealed that MyoInteract allowed novices in biomechanical RL to successfully setup, train, and assess goal-directed user movements within a single session. By transforming biomechanical RL from a days-long expert task into an accessible hour-long workflow, this work significantly lowers barriers to entry and accelerates iteration cycles in HCI biomechanics research.

08.
medRxiv (Medicine) 2026-06-22

Why drinking episodes escalate differently: Event-level pathways linking hazardous alcohol consumption and sexual risk

Background: Alcohol-involved drinking episodes vary in whether they involve hazardous alcohol consumption alone, near-miss sexual risk, or sexual risk behavior, but the within-event mechanisms underlying this variability remain unclear. Methods: Guided by syndemic theory, we conducted a qualitative event-level analysis using modified grounded theory among adults in the San Francisco Bay Area who reported hazardous alcohol consumption, defined as an Alcohol Use Disorder Identification Test score [≥]16. In-depth interviews elicited narratives of recent heavy drinking episodes and yielded 64 discrete drinking events across 22 participants. We focused on 35 events with evidence of within-event interaction between biopsychosocial and contextual factors. Using constant comparison, we identified escalation pathways, characterized interruption, and examined how events diverge into three outcomes: hazardous alcohol consumption only, hazardous alcohol consumption with near-miss sexual risk (when risk was plausible but not enacted), and hazardous alcohol consumption with sexual risk behavior. Results: Two primary escalation pathways emerged. Dose-driven escalation involved cumulative alcohol or substance exposure that progressively impaired awareness and self-regulation. Meaning-driven escalation involved prioritizing connection, intimacy, or belonging despite awareness of risk. Time-driven continuation extended exposure across contexts and amplified both pathways. Hazardous alcohol consumption-only events more often followed dose-driven pathways, whereas events involving sexual risk behavior more often followed meaning-driven pathways. Near-miss events occurred across both pathways and illustrated how interruption before the escalation constraint point, when the capacity to modify behavior became reduced, could redirect escalation before sexual risk behavior occurred. Across events with similar levels of intoxication narratives, outcomes diverged according to when the interruption occurred and whether it altered escalation. Conclusion: Hazardous drinking episodes diverge into different outcomes based on escalation pathways and the timing and effectiveness of interruption. Early and effective interruption before the escalation constraint point may represent a key target for harm-reduction strategies to prevent progression to sexual risk behavior.

09.
arXiv (CS.CV) 2026-06-16

A Survey on 3D Skeleton Based Person Re-Identification: Taxonomy, Advances, Challenges, and Interdisciplinary Prospects

Person re-identification via 3D skeletons is an important emerging research area that attracts increasing attention within the pattern recognition community. With distinctive advantages across various application scenarios, numerous 3D skeleton based person re-identification (SRID) methods with diverse skeleton modeling and learning paradigms have been proposed in recent years. In this paper, we provide a comprehensive review and analysis of recent SRID advances. First of all, we define the SRID task and provide an overview of its origin and major advancements. Secondly, we formulate a systematic taxonomy that organizes existing methods into three categories centered on hand-crafted, sequence-based, and graph-based modeling. Then, we elaborate on the representative models along these three types with an illustration of foundational mechanisms. Meanwhile, we provide an overview of mainstream supervised, self-supervised, and unsupervised SRID learning paradigms and corresponding common methods. A thorough evaluation of state-of-the-art SRID methods is further conducted over various types of benchmarks and protocols to compare their effectiveness, efficiency, and key properties. Finally, we present the key challenges and prospects to advance future research, and highlight interdisciplinary applications of SRID with a case study.

10.
arXiv (CS.AI) 2026-06-17

A Machine-Learned Comorbidity Index

arXiv:2606.17450v1 Announce Type: new Abstract: Traditional comorbidity scores (e.g., Charlson and Elixhauser) are widely used for risk adjustment and patient stratification, but they have two key limitations: (i) they are largely mortality-centric and do not align well with other clinical outcomes, and (ii) their linear, rule-based structure cannot capture nonlinear, outcome-specific risk relationships. We propose a Machine-Learned Comorbidity Index (MLCI) that maps diagnosis codes to a single scalar by maximizing the normalized Hilbert-Schmidt Independence Criterion (nHSIC) between the learned score and multiple clinical outcomes. MLCI captures nonlinear risk-outcome dependence and is supported by a theory that characterizes when a unified, informative admission-level ordering can be achieved across outcomes. Empirical results on multiple benchmark electronic health record (EHR) datasets show that MLCI outperforms strong baselines across multiple evaluation metrics.

11.
arXiv (math.PR) 2026-06-16

Balanced affine Motzkin paths: Pearson geometry and global endpoint asymptotics

arXiv:2601.17634v2 Announce Type: replace Abstract: We study endpoint distributions of balanced affine weighted Motzkin paths. In the balanced case, the generating-function equation has Pearson-type characteristic geometry. We show that this geometry controls the terminal-height law globally: the characteristic escape time determines the limiting cumulant generating function, the large-deviation rate function, and the ray-scale asymptotics. Thus the usual Gaussian window is only the local quadratic approximation to a global Pearson-driven profile. For finite sizes, we prove a uniform Daniels saddlepoint approximation in the one-dominant-singularity regimes and identify the exceptional antipodal case requiring a lattice/interference correction.

12.
medRxiv (Medicine) 2026-06-18

Hospital staff views on the visibility, role and impact of Acute Learning Disability Liaison Services in Wales: a service evaluation

People with a learning disability experience marked health inequalities. In Wales, Acute Learning Disability Liaison Services (ALDLS) are delivered by specialised learning disability services, and all roles within them are undertaken by Learning Disability Liaison Nurses (LDLN). These services aim to enable access to, and delivery of, secondary care by supporting reasonable adjustments, facilitating communication, and coordinating care for people with learning disability during hospital encounters. However, independent evidence of the impact of ALDLS on patient care remains limited. This evaluation tries to address this evidence gap by examining hospital staff perceptions of the visibility, role, and impact of ALDLS across Welsh Health Boards, with the aim of informing service design and development and improving secondary care access and care for people with learning disability. The service evaluation used a qualitative approach involving interviews and a focus group with hospital staff across the seven Welsh Health Boards who had experience working with or interacting with ALDLS staff to care for patients with learning disability. Findings cover six key areas including i) visibility and delivery of ALDLS, ii) Barriers and challenges to effective ALDLS delivery, iii) Enablers of effective ALDLS delivery, iv) Positive impacts for patients with learning disability, v) Negative impacts and unintended consequences when the service is absent or limited, and vi) Participants recommendations for future improvements of ALDLS. To synthesise the findings, we developed an overview diagram, which illustrates how ALDLS may influence care quality in acute hospitals. The overview places the liaison service at the centre, showing how organisational enablers and barriers shape its delivery, and how its core functions support improvements in safety, timeliness, effectiveness, efficiency, equity, and patient-centred care. From the findings we have identified recommendations for practice and policy. These include that ALDLS should be recognised as a core, safety-critical component of acute hospital care for people with a learning disability, rather than an optional add-on. In practice, services should be more visibly embedded within routine pathways, with consistent site-based presence, clear referral criteria, early identification through electronic flagging and notification systems, and routine involvement in multidisciplinary planning for complex admissions and procedures. At policy level, ALDLS provision should be recognised within equality and patient safety frameworks as an essential service requiring sustained investment, national minimum configuration standards, adequate staffing, and better-integrated digital systems to support continuity, equitable access, and person-centred care.

13.
arXiv (CS.CL) 2026-06-25

When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stance

作者:

Can a statistically significant, large-effect-size finding in computational social science be entirely an artifact of the measurement instrument? We present a case where the answer appears to be yes. Analyzing 85 interviews across four public intellectuals (2016–2026), we find a robust negative-affect/emphatic-certainty lexical co-occurrence pattern under keyword-based scoring ($r = 0.72$–$0.93$, $p < 0.01$ for all four speakers). Replacing keyword counting with LLM-based zero-shot semantic classification on the complete diarized corpus (32,625 sentences) dramatically reduces this correlation: Dalio's $r = 0.851$ drops to $r = 0.206$, with two speakers showing negative $r(neg, emphatic)$ and one showing null. In contrast, the LLM reveals a strong negative-hedging coupling across speakers – Rogoff's $r(neg, hedged) = 0.875$ ($p = 0.001$) and Zeihan's $r(neg, hedged) = 0.722$ ($p = 0.008$) – consistent with the conventional expectation that pessimistic discourse attracts hedging, not certainty. Sentence-level error analysis traces this discrepancy to three structural failure modes in keyword lexicons – syntactic blindness, polysemy blindness, and categorical absence – illustrated through cases where keyword counting inverts semantic meaning (e.g., ''never absolutely totally confident'' scored as high-certainty). We argue that keyword lexicons measure a universal lexical co-occurrence tendency – negative discourse naturally attracts emphatic vocabulary – that is orthogonal to, and can systematically invert, rhetorical stance. Treating keyword counts as measurements of epistemic certainty is a category error: a finding that appears to be about a speaker's psychology may be entirely about the counting of words.

14.
arXiv (CS.CL) 2026-06-15

Same-Origin Policy for Agentic Browsers

Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instructions. The same-origin policy (SOP) is a fundamental browser security mechanism that prevents unauthorized automated cross-origin data flows induced by scripts. However, whether SOP remains effective in agentic browsers is an open question that has not been systematically studied. In this work, we bridge this gap. We first observe that an agentic browser can itself serve as an automated channel for cross-origin data flows, potentially leading to SOP violations. To investigate this phenomenon, we construct SOPBench, a benchmark for evaluating SOP violations in agentic browsers. Our evaluation shows that existing agentic browsers frequently violate SOP, both in benign settings and under attacks. To address this problem, we propose SOPGuard, an SOP enforcement mechanism tailored to agentic browsers. We implement SOPGuard in BrowserOS, an open-source agentic browser. Extensive evaluations demonstrate that SOPGuard effectively enforces SOP while preserving utility and incurring only a small runtime overhead. Our code and data are available at https://github.com/wxl-lxw/BrowserOS-SOPGuard.

15.
medRxiv (Medicine) 2026-06-10

Impact of Early Treatment on Symptom Improvement and Procedural Events among Men with BPH and Bothersome Lower Urinary Tract Symptoms: A Contemporary Analysis of the American Urological Association Quality (AQUA) Registry

PURPOSE: As the armamentarium of BPH therapies continues to expand, it remains imperative to maximize patient satisfaction and minimize decisional regret. We sought to determine the impact of time from BPH diagnosis to index treatment on symptom improvement and subsequent procedural events. MATERIALS AND METHODS: We queried the American Urological Association Quality Registry for men [&ge;] 40 years old with BPH, available IPSS data, and no receipt of prior BPH treatment. Index treatment included medication, surgery, or minimally invasive surgical therapy (MIST). Outcomes included IPSS over 3 years of follow-up, change in percentage of mild lower urinary tract symptoms (LUTS) by 3 months, and time to procedural event. Patients were stratified by time from index diagnosis to treatment by 3 years. Outcomes were compared across time-to-treatment cohorts with appropriate statistical tests with p < 0.05 as significant. RESULTS: 43,919 patients met criteria with 19,642 pursuing treatments. Patients pursued treatment at comparably lower baseline IPSS compared to prior prospective series. Patients undergoing surgery and MIST had significantly higher baseline IPSS, while medical comorbidities were significantly more common among men initiating pharmacotherapy. Early surgery and MIST were associated with significant improvement in IPSS within 6-12 months and an increase in mild LUTS by 3 months. All forms of early treatment were associated with delayed time to procedural events, including catheterization and fulguration. CONCLUSIONS: Early procedural intervention for BPH is associated with early symptom improvement and delayed time to procedural events among real-world, contemporary practice.

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

CoAgent: Concurrency Control for Multi-Agent Systems

arXiv:2606.15376v1 Announce Type: cross Abstract: Multi-agent LLM systems – coding agents, devops agents, document agents – now routinely run several agents in parallel against the same git tree, Kubernetes cluster, or document. As soon as two of them mutate shared state, they enter the regime classical concurrency control has studied for decades, but classical mechanisms fit LLM agents poorly. A single agent transaction spans minutes of inference, read sets are broad and opaque rather than statically inferable, and the live state agents act on admits neither fork nor buffer, so writes take effect the moment they execute. Locks block long inference intervals; OCC abort-and-retry discards minutes of work on every conflict. This paper builds concurrency control on a capability classical transactions lack: the LLM inside each agent can judge whether a conflicting write invalidates its plan, and can repair exactly the operations that depended on it. Control therefore turns advisory: the runtime informs, the agent repairs. Our protocol, MTPO (Monotonic Trajectory Pre-Order), fixes a serialization order at launch, serves each read the order-filtered value, and applies writes speculatively in place; a one-way notification asks an affected reader to re-judge and patch its plan, while the framework mechanically undoes and reorders misplaced writes through the saga-style inverse each tool registers in advance. At quiescence the run is serializable in the pre-decided order. We realize MTPO as CoAgent, toolcall middleware whose privileged ToolSmith grows footprint-declared, undoable tools online. On ten contended workloads, CoAgent stays within 5\% of serial correctness at a $1.4\times$ speedup and near-serial token cost, where 2PL and OCC surrender nearly all concurrency gains; on a bash-only target system, it grows a 25-tool library online and lifts the task pass rate from 45/71 to 63/71 at $0.80\times$ the time and $0.86\times$ the cost.

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

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

Instruction-based image editing has made notable progress with recent advances in generative models. However, the quality of the edited result is still influenced by the randomly sampled initial noise, particularly in complex editing scenarios. An unsuitable initial noise may lead to unsatisfactory editing results. Recent inference-time scaling methods address this issue by sampling multiple initial noises and selecting better candidates. Nevertheless, most of them follow a decode-then-verify scheme which introduces an efficiency-accuracy trade-off. When decoding is performed after limited inference steps, the decoded images often remain too noisy for reliable assessment, whereas sufficiently denoised images require much higher computational cost. To address this issue, we propose VeriLatent, a plug-and-play adaptive inference-time scaling framework with early-step latent verification for image editing. Specifically, we propose a novel verifier that scores each initial noise through a latent-space editing activation map at an early stage. It identifies promising candidates by assessing whether they can induce an effective edit in the correct region. This enables efficient early pruning without decoding latents into images. Building on this, we further develop an adaptive search strategy for inference-time scaling. It allocates inference budgets according to editing difficulty, thereby reducing the number of function evaluations (NFE). Extensive experiments on multiple benchmarks and different base models demonstrate that VeriLatent consistently improves both editing performance and inference-time scaling efficiency.

18.
arXiv (CS.AI) 2026-06-24

Maestro Order: A Model-Agnostic Orchestration Harness

作者:

arXiv:2606.23983v1 Announce Type: cross Abstract: A single forward pass of a capable model is a fast, fluent, and unreliable problem-solver: it is right often enough to be useful and wrong often enough to be dangerous; in language models, such confident errors are known as hallucinations. We present Maestro Order, a model-agnostic orchestration harness that turns unreliable solvers into reliable problem-solving systems by composing them according to four structural primitives (decompose, ensemble, verify, and recurse) and a budget-aware controller that decides where to spend compute. The harness treats any model as a black-box base solver behind a uniform interface, layers a verifier ensemble whose discrimination is measured online, and allocates verification and voting to the stages with the highest marginal reliability per unit cost. We give the architecture, the message and state schema, the controller algorithm, and the engineering that makes it deterministic, observable, and fault-tolerant. We then specify an evaluation methodology (reliability at fixed cost, coverage, calibration, and ablations) and report results from a faithful Monte Carlo simulation of the harness over a parameterized solver/verifier model. The simulation reproduces the predicted laws quantitatively: verification amplifies reliability geometrically (e.g. $0.55\to0.98$ with two gates, $\to0.999$ with four), voting helps only above chance and is limited by shared errors, and a budget-aware controller reaches a target reliability at a small fraction of the cost of voting alone by selecting the cheapest mechanism for each regime. We close with failure modes (verifier gaming, correlated errors, and decomposition error compounding) and concrete guidance: build robust checkers, diversify solvers, and let the controller put compute where the information is.

19.
arXiv (CS.AI) 2026-06-12

LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis

arXiv:2606.13220v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as interactive assistants for technical problem solving. However, when users provide incomplete descriptions or plausible but unverified explanations, LLMs may prematurely align with these assumptions and propose solutions before collecting sufficient evidence. We refer to this behavior as user-driven sycophancy: the tendency of an LLM to reinforce a user-provided hypothesis instead of testing alternative explanations. This paper introduces LLM-as-an-Investigator, an evidence-first agentic AI methodology for robust problem diagnosis. The approach is implemented through a Solution Investigator Agent, which estimates the ambiguity of an initial problem description, generates candidate hypotheses, asks targeted clarification questions, and updates hypothesis probabilities after each answer. Rather than producing an immediate response, the agent continues the investigation until the evidence makes one candidate explanation stronger than the alternatives. To evaluate the approach, we build a benchmark from solved technical forum threads in mechanical, electrical, and hydraulic domains. We use a three-agent evaluation pipeline in which a Problem-Solution Extractor Agent converts solved threads into structured cases, a Ground-Truth Evaluator Agent simulates the user while hiding the known solution, and the tested assistant attempts to recover the solution through dialogue. The experiments compare standard assistants, reasoning-oriented LLMs, and the proposed investigator-based model across LLM backbones. In addition to diagnostic accuracy, we analyze how standard assistants follow misleading user hypotheses in diagnostic cases. The results show that the proposed approach identifies the problem more accurately than direct prompting and reasoning-only baselines, while its evidence-first protocol helps reduce user-induced conversational bias.

20.
arXiv (CS.LG) 2026-06-25

Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration

arXiv:2606.24970v1 Announce Type: new Abstract: Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy. As attention layers are the most resource-intensive parts of LLMs, pruning them is a promising compression strategy. Prior work shows that up to 33% of attention layers can be pruned with minimal accuracy loss. Nevertheless, the impact of attention pruning on model interpretability, specifically faithfulness and confidence calibration, remains unstudied. To address this gap, we study how pruning attention layers affects explanation faithfulness and confidence calibration across five LLMs and eight datasets. While the pruned models often maintain high accuracy, we find that their faithfulness and calibration often degrade. Notably, faithfulness and calibration can fluctuate significantly, even when accuracy remains stable, highlighting a misalignment between model confidence, interpretability, and accuracy. Our findings suggest that layer pruning can affect LLMs' interpretability and reliability in ways not captured by accuracy and efficiency measures alone. We recommend including explainability and calibration metrics when evaluating pruned models.

21.
arXiv (quant-ph) 2026-06-16

Counterdiabatic Raman Atom Optics for Compact High-Sensitivity Gravimetry

arXiv:2606.16945v1 Announce Type: new Abstract: Large-momentum-transfer (LMT) atom interferometry provides a route toward enhanced inertial sensitivity in compact quantum sensors, but its scalability is limited by the accumulation of pulse-transfer errors across long Raman pulse sequences. We investigate theoretically the use of stimulated Raman shortcut-to-adiabatic passage (STIRSAP) for high-fidelity LMT atom optics in a Mach–Zehnder interferometer geometry. The counterdiabatic correction is encoded directly into the Raman pulse envelopes, eliminating the need for auxiliary microwave or radio-frequency control fields. Numerical simulations based on an effective Raman model show that $1~\mu\mathrm{s}$ STIRSAP pulses achieve single-pulse transfer fidelities of $F_\pi = 0.99902$ while maintaining negligible pulse-time overhead even at high momentum order. We analyze the resulting tradeoff between interferometric phase enhancement and compound contrast decay and identify an unconstrained shot-noise optimum near $n\approx270$. The analysis further shows that practical operation at extreme LMT order is constrained by wave-packet separation, vibration noise, Doppler detuning, and accumulated systematic effects rather than by pulse duration itself. These results establish superadiabatic Raman control as a promising approach for scalable high-fidelity atom optics and clarify the physical limitations governing compact high-order atom interferometers.

23.
arXiv (CS.AI) 2026-06-15

FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization

arXiv:2606.13737v1 Announce Type: cross Abstract: Stream guardrails enable token-level safety detection before full responses are generated. However, they often make overly conservative judgements and block those sensitive but safe tokens, which is known as over-refusal. Due to lack of full context, they also fail to detect implicitly harmful content from jailbreaking. To address these challenges, we propose FreoStream, a novel streaming guardrail framework. Specifically, FreoStream fine-tunes a LoRA module to perform Future-Aware Reasoning when the base guardrail detects unsafe tokens. The reasoning process follows a Future-Reason-Judge paradigm: predict the future, reason about the full context and give the final judgement. This design can effectively reduce over-refusal by incorporating the future information. Moreover, we introduce the Safety-Aligned Optimization module that extracts the safety-aligned component from the reasoning gradients to update the base guardrail model, thereby enhancing streaming safety detection. Extensive experiments on various safety benchmarks demonstrate that FreoStream achieves lower over-refusal rates and better jailbreak defense compared to existing streaming guardrails.

24.
arXiv (CS.AI) 2026-06-12

Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning

arXiv:2505.04021v3 Announce Type: replace-cross Abstract: Inference providers must maintain availability for many LLMs, including low-volume but essential models, making resource efficiency increasingly important as token prices fall. Analysis of production traces reveals a dynamic bursty-group pattern in which sets of models become active together and shift over time; existing space- and time-sharing approaches lack principled mechanisms to adapt to this variability, forcing trade-offs between SLO adherence and efficiency. We observe that elastic memory allocation can unify spatial and temporal sharing. Based on this insight, we have developed Prism, a memory-centric LLM co-serving framework that applies memory ballooning to reclaim memory across models and support both forms of sharing under a single scheme. Prism's balloon driver, referred to as kvcached, has been open-sourced at https://github.com/ovg-project/kvcached, and deployed in production environments across 10K+ GPUs.

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

ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark

Large language models (LLMs) are increasingly applied to symbolic mathematics, yet existing evaluations often conflate pattern memorization with genuine reasoning. To address this gap, we present ASyMOB, a high-resolution dataset of 35,368 validated symbolic math problems spanning integration, limits, differential equations, series, and hypergeometrics. Unlike prior benchmarks, ASyMOB systematically perturbs each seed problem using symbolic, numeric, and equivalence-preserving transformations, enabling a fine-grained assessment of generalization. Our evaluation reveals three key findings: (1) most models' performance collapses under minor perturbations, while top systems exhibit an apparent regime shift in robustness; (2) integrated code tools stabilize performance, particularly for weaker models; and (3) we identify examples where Computer Algebra Systems (CAS) fail while LLMs succeed, as well as problems solved only via a hybrid LLM-CAS approach, highlighting a promising integration frontier. ASyMOB serves as a principled diagnostic tool for measuring and accelerating progress toward building verifiable, trustworthy AI for scientific discovery.