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 (quant-ph) 2026-06-24

Quantum-enabled active matter at the atomic scale

arXiv:2606.24615v1 Announce Type: new Abstract: Active matter comprises particles that extract energy from their local environment and convert it into motion. Although active particles have been miniaturized down to the nanoscale, realizing activity at the fundamentally smaller scale of individual atoms remains an open challenge, where quantum effects become increasingly relevant. Here, we experimentally demonstrate that individual Cs-133 atoms confined in an optical dipole trap extract energy from an ultracold bath of Rb-87 atoms via quantum-mechanical spin interactions and convert it into active motion. We quantitatively reproduce the resulting dynamics using a parameter-free active Langevin model derived from kinetic theory and support it with event-driven Monte Carlo collision simulations. The microscopic origin of activity is identified as quantum spin exchange, which transfers discrete internal spin energy into kinetic motion. Our work establishes a quantum-enabled route to active matter at the fundamental size limit of single atoms and opens perspectives for exploring the interplay of activity, quantum physics, and mesoscopic non-equilibrium thermodynamics.

02.
arXiv (CS.AI) 2026-06-19

The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction

arXiv:2603.01250v2 Announce Type: replace-cross Abstract: Breast cancer is the most frequently diagnosed malignancy among women worldwide and a leading cause of cancer-related mortality. Dynamic contrast-enhanced magnetic resonance imaging plays a central role in tumor characterization and treatment monitoring, particularly in patients receiving neoadjuvant chemotherapy. However, existing artificial intelligence models for breast magnetic resonance imaging are typically developed and evaluated using heterogeneous datasets, study populations, and assessment protocols, making direct comparison difficult and limiting understanding of model robustness across institutions and clinically relevant patient subgroups. The MAMA-MIA Challenge was designed to address these challenges by providing a standardized benchmark for the joint evaluation of primary tumor segmentation and prediction of pathologic complete response using pre-treatment magnetic resonance imaging only. The training cohort comprised 1,506 patients from multiple institutions in the United States, while evaluation was conducted on an external test set of 574 patients from three independent European centers to assess cross-continental and cross-institutional generalization. A unified scoring framework combined predictive performance with subgroup consistency across age, menopausal status, and breast density. Twenty-six international teams participated in the final evaluation phase. Results demonstrate substantial performance variability under a common external evaluation framework and reveal trade-offs between overall accuracy and subgroup fairness. The challenge provides standardized datasets, evaluation protocols, and public resources to promote the development of robust and equitable artificial intelligence systems for breast cancer imaging.

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

ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control

arXiv:2606.16605v1 Announce Type: new Abstract: World models are widely used in robotic and agentic engineering control systems due to their ability to learn latent dynamics for planning and decision-making. As these systems are increasingly deployed in safety-critical settings, understanding their robustness under adversarial conditions has become essential. However, existing evaluations lack a unified benchmark for testing adversarial threats across the policy, value, and latent-dynamics levels of world-model agents. To fill this gap, we present ARB4WM, a unified evaluation framework for pre-deployment robustness and risk assessment of world-model agents under visual perturbations. ARB4WM defines five white-box loss objectives across these three levels and studies their effects when combined with single-step or multi-step perturbation strategies and temporal attack modes, including full-frame, half-sequence, and sparse-frame exposure. Specifically, we evaluate four Dreamer-style agents across 20 tasks from MetaWorld and the DeepMind Control Suite under different loss objectives, perturbation strategies, and temporal attack modes. Results show that attacks targeting value estimation, latent representations, and RSSM dynamics can be as damaging as direct policy disruption, and that early or frequent perturbations are especially harmful, while input-level defenses provide limited recovery under adaptive attacks. These findings suggest that safety, risk, and reliability assessment for world models should cover multiple component-oriented attack objectives and temporal exposure protocols rather than relying solely on action-space robustness. Source code is available at https://github.com/zaoanguai/ARB4WM.

04.
arXiv (quant-ph) 2026-06-12

Multi-entropy in heavy local quenches

arXiv:2606.12526v1 Announce Type: cross Abstract: We study the time evolution of tripartite entanglement in heavy local quenches in two-dimensional holographic conformal field theories. Our diagnostic is the genuine multi-entropy of adjacent intervals, computed from both bulk and boundary perspectives. A perturbative bulk analysis shows that the first-order small-mass perturbation around the vacuum geodesic network cancels identically at any time after the quench. In the fully back-reacted geometry, a vacuum-subtracted genuine multi-entropy arises from a mismatch between the winding selected by the trivalent geodesic network and the windings selected independently by the pairwise geodesics. In the sharp quench limit, the time dependence of genuine multi-entropy is kinematically fixed to logarithms of rational functions of time and is independent of the heavy operator dimension. The CFT calculation reproduces the same formula within the heavy-light vacuum block approximation, where the branch choice in the heavy-background uniformization map corresponds to the winding selection in the bulk. These results indicate that, in this setup, the genuine multi-entropy is controlled by global saddle selection, rather than by a local energy response or quasiparticle propagation.

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

Depth-Attention: Cross-Layer Value Mixing for Language Models

Self-attention selects information freely across the sequence, but across depth, Transformers merely add each layer's output to the residual stream, so later layers cannot selectively reuse earlier-layer representations. Recent cross-layer methods improve this flow but operate on hidden states outside attention, adding state beyond the key-value cache at inference–a cost that becomes increasingly salient as modern LLMs compress the cache with grouped-query and multi-head latent attention. We introduce Depth-Attention, which performs this selection inside the attention module itself: before a layer attends over the sequence, its query attends over the keys of earlier layers at the same token position and mixes their values into the value that self-attention then reads. Because Depth-Attention reuses the standard attention queries, keys, and value-cache slots, storing depth-mixed values in place of the original values, it adds no parameters and introduces no persistent inference state beyond the standard key-value cache–the same cache size as a vanilla decoder and less than hidden-state-based cross-layer methods. On Qwen3-style decoders at 1.5B and 3B parameters, Depth-Attention attains the lowest perplexity and the highest average downstream accuracy, improving over the vanilla Transformer by up to 2.3 accuracy points and surpassing strong cross-layer baselines in perplexity and average accuracy, while adding under 0.01% extra arithmetic FLOPs and no additional persistent inference state. The gains hold from 360M to 3B parameters and extend to looped Transformers.

06.
Nature (Science) 2026-06-22

C-glycoside synthesis via radical cross-coupling of glycohydrazides

作者:

Carbohydrates are among the most abundant and structurally diverse biomolecules in nature, playing central roles in energy storage, molecular recognition, and cell signaling. Within this domain, C-glycosides1-3, in which the oxygen atom of the glycosidic bond in O-glycosides is replaced by carbon, have emerged as valuable motifs in medicinal chemistry due to their resistance to enzymatic hydrolysis2,4. Of particular importance are C-aryl glycosides, exemplified by the SGLT2 inhibitors dapagliflozin, canagliflozin, and empagliflozin, which are frontline therapies for type 2 diabetes5-7. However, scalable syntheses of C-aryl glycosides have traditionally relied on protected sugar derivatives, lengthy sequences, or conventional cross-couplings that often suffer from poor selectivity, limited scope, and extensive protecting-group manipulation6. Herein, we report a practical approach to C-aryl glycosides using glycosyl sulfonyl hydrazides as redox-neutral radical precursors for cross-coupling. Prepared directly from unprotected native sugars, these reagents generate glycosyl radicals under mild conditions and enable efficient access to diverse C-aryl glycosides, including all approved SGLT2 inhibitors, natural products such as salmochelins and neopetrosins, and medicinally relevant probes. Beyond anomeric functionalization, this platform enables C–C bond formation at multiple positions on carbohydrate scaffolds and supports stereoretentive radical coupling that can override inherent stereochemical biases, expanding practical access to carbohydrate-derived therapeutics and chemical tools.

07.
arXiv (CS.CV) 2026-06-19

FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows

Conditional diffusion and flow models routinely fail to satisfy the very constraints that define their task. For instance, a depth-conditioned model often produces images whose re-extracted depth disagrees with the input, even though the forward operator–the depth predictor defining the constraint–is available during both training and inference. Existing approaches generally fall into two categories: supervised models that treat the conditioning signal as a static cue and ignore alignment information at inference, and guidance-based methods that consult it through hand-tuned linear updates, typically trading fidelity to the condition against the plausibility of the generated sample. We argue that the fundamental gap in both paradigms is that the model is never trained to utilize its own alignment error. We introduce FlowBender, a closed-loop framework that treats this error as a first-class input, training the network to learn a correction policy conditioned on inference-time feedback. At each step, an unguided look-ahead pass estimates the clean signal, a task-specific deviation is computed via the forward operator, and a refinement pass consumes this signal to produce a corrected velocity. We propose several variants of FlowBender, including a gradient-based formulation for differentiable operators and a zero-order variant for non-differentiable settings such as JPEG compression. For efficient sampling, we introduce a prior-step shortcut that enables closed-loop correction at a minimal additional computational cost. Across image-to-image translation, restoration, and 3D mesh texturing, FlowBender consistently outperforms standard supervised baselines, alignment-loss-augmented training, and state-of-the-art inference-time guidance, improving fidelity and plausibility simultaneously rather than trading them against each other. Project page: https://flow-bender.github.io/

08.
medRxiv (Medicine) 2026-06-15

Artificial Intelligence-Based Detection of Airway Mucus Plugs on CT and Associations With Clinical Outcomes in COPDGene

RATIONALE: Airway mucus plugging is a clinically relevant manifestation of airway pathology in chronic obstructive pulmonary disease (COPD) and is associated with increased mortality even in early disease; however, visual computed tomography (CT) assessment is subjective and labor intensive. OBJECTIVES: To develop an AI-based quantitative CT method for automated detection of airway mucus plugging and evaluate associations with physiologic impairment and clinical outcomes. METHODS: Inspiratory CT scans from 8,971 COPDGene Phase 1 (GOLD 0-4 and PRISm) participants were analyzed. An AI-based framework combining 3D airway segmentation discontinuities and convolutional neural network classification identified mucus plug obstructions, yielding mucus plug burden (total plug count). Associations with outcomes were evaluated using covariate-adjusted models. MEASUREMENTS AND MAIN RESULTS : Higher mucus plug burden was associated with lower post-bronchodilator FEV % predicted ({rho} = -0.41; P < 0.001), greater air trapping (LAA < -856 HU; {rho} = 0.33; P < 0.001), worse health status (SGRQ; {rho} = 0.31; P < 0.001), and shorter 6-minute walk distance ({rho} = -0.26; P < 0.001). Among GOLD 1-4 participants, mucus plug presence was independently associated with increased all-cause mortality (adjusted hazard ratio, 1.28; P < 0.005) and exacerbation frequency (adjusted incidence rate ratio, 1.32; P < 0.005). Plug presence was also associated with increased respiratory mortality across GOLD categories and cardiovascular mortality in GOLD 1-2. CONCLUSIONS: AI-based quantitative CT assessment of airway mucus plugging provides a scalable, reproducible measure associated with physiologic impairment and adverse outcomes in COPD, supporting its role in risk stratification and future therapeutic studies.

09.
arXiv (CS.CL) 2026-06-15

ClaimFlow: Tracing the Evolution of Scientific Claims in NLP

Scientific papers advance $claims$ that later work supports, extends, or sometimes refutes. Yet existing methods for citation and claim analysis capture only fragments of this dialogue. In this work, we make these interactions explicit at the level of individual scientific claims. We introduce $\texttt{ClaimFlow}$, a claim-centric view of the NLP literature, built from $1{,}617$ ACL Anthology papers $(1979 - 2025)$ that are manually annotated with $5{,}689$ claims and $4{,}871$ cross-paper claim relations, indicating whether a citing paper $\texttt{supports}$, $\texttt{extends}$, $\texttt{qualifies}$, $\texttt{refutes}$, or references a cited claim as $\texttt{background}$. Building on $\texttt{ClaimFlow}$, we define a new task – $Claim Relation Classification$ – which requires models to infer the scientific stance toward a cited claim from the text and citation context. Evaluating neural models and large language models on this task, we report baseline performance of $0.81$ macro-F1, suggesting that the task is tractable while leaving room for improvement. We then scale this framework to $\sim$$13k$ NLP papers to study claim evolution across decades of NLP research. We show that $63.5\%$ claims are never reused; only $11.1\%$ are ever challenged. Widely propagated claims are more often $reshaped$ through qualification and extension than supported or refuted. Overall, $\texttt{ClaimFlow}$ offers a lens for examining how ideas shift and mature within NLP.

10.
medRxiv (Medicine) 2026-06-23

Antibodies against influenza A/H1N1pdm2009 and B/Victoria strains but not A/H3N2 are increased in recent onset type 1 narcolepsy versus matched controls

Study Objectives: Onsets of Narcolepsy type-1 (NT1) increased following A/H1N1 vaccination with PandemrixTM in Europe and with A/H1N1pdm2009 infections in China and other countries. To test if other strains could trigger narcolepsy, we measured strain-specific antibodies in patients with recent onset NT1 compared to controls. Methods: Antibodies against hemagglutinin (HA) and neuraminidase (NA) were tested in 62 patients with very recent onset (onset and blood collection following a single flu season, mean +/- SEM: 0.44 +/- 0.06 years since onset) and 100 controls matched by age, sex, season and year of collection (2000-2025). Results were next extended to 181 recent onset patients (mean +/- SEM: 1.00 +/- 0.05 years) versus 260 controls, matched by sex, season and year, but having a slightly higher mean age. HA inhibition (HAI) and NA inhibition (NAI) assays were conducted using flu strains known to circulate during the corresponding flu seasons. HAI results are shown as % positive (titers >= 40) and NAI results as geometric mean titers. Odds ratio (OR) and coefficient were used to compare antibody titers in NT1 versus controls. The contribution of each assay to prediction was finally quantified in the larger sample set using Shapley decomposition. Results: NT1 patients had increased anti-HA and anti-NA antibodies against A/H1N1pdm2009 (anti-HA OR = 3.86, anti-NA coefficient = 0.35) and B/Victoria (anti-HA OR =1.90, anti-NA coefficient = 0.22), but not A/H1N1pre2009, A/H3N2, or B/Yamagata, independent of HLA-DQB1*06:02 status, age, sex, and flu season. Correlations between anti-HA and anti-NA antibodies titers were weak to moderate but significant (r2=-0.10 to 0.34). Multivariable model outperformed age-only baseline (McFadden R2 = 0.19 vs. 0.03; AUC = 0.79 vs. 0.64; likelihood-ratio test X2 = 51, p

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

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution–properties absent from existing datasets. We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm that addresses these gaps jointly. Stage 1 constructs roughly 50000 structured intents via a 4D framework (Persona x Domain x Task x Complexity); after deduplication the pool contains 43956 unique intents and attains a Vendi Score of 61.57 over the entire pool on mpnet-base-v2 embeddings (cosine kernel, q=1). Stage 2 drives multi-turn user-agent interaction through a role-locked user simulator that grounds each user turn in actual execution outcomes, producing 23132 complete trajectories averaging 8.12 user turns and 68.24 total dialogue turns. Stage 3 runs every tool call inside a live, isolated OS workspace, generating authentic failure-recovery dynamics instead of simulated responses. Fine-tuning on ISETrace improves ClawEval pass@1 from 19.3 to 37.7 using Qwen3-8B on agent tool-use tasks with a standard protocol. This result outperforms zero-shot GPT-4o and the larger Qwen3-32B base model which is four times bigger. An ablation on Stage 2 proves multi-turn simulation brings a large portion of the performance gain. We release all source code and dataset at https://github.com/Valiere01/ISE-Trace.

12.
arXiv (CS.CL) 2026-06-16

Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models

Multilingual large language models (LLMs) depend on subword tokenization to bridge discrete text and continuous neural representation. State-of-the-art multilingual LLMs often use Byte-level Byte-Pair Encoding (BPE) tokenizers that structurally favor high-resource languages and Latin scripts. For speakers of underrepresented languages, particularly those across Southeast Asia, this bias inflates inference costs and widens cross-lingual capability gaps. We present the first systematic comparison of equitable tokenizers on a unified benchmark spanning 11 Southeast Asian languages. Beyond tokenizer-level analysis of compression efficiency and cross-lingual equity, we assess downstream task performance through controlled 1.5B-parameter language model training using the same training data. Our results show that Parity-aware BPE lies on the Pareto frontier of the efficiency-equity trade-off, achieving strong compression parity at competitive cost. Morphology-Driven Byte Encoding delivers the best semantic reasoning performance through morphologically richer representations, albeit at a higher computational expense. Byte Latent Transformer underperforms on downstream tasks, possibly because its architectural assumptions misalign with the constraints of limited low-resource training data. Together, our findings demonstrate that cross-lingual fairness and tokenization efficiency are not fundamentally at odds, and offer practical guidance for designing equitable multilingual models.

13.
bioRxiv (Bioinfo) 2026-06-19

Identification of Altered Potassium Channels for Drug Repurposing in Long COVID Patients

Long COVID (LC) is a complex condition characterized by persistent, chronic multisystem manifestations, with a significant proportion of patients exhibiting neurological symptoms. Human ion channels (HICs), particularly potassium channels, are abundantly expressed in the nervous system and linked to key metabolic processes, making them potential candidates for understanding LC pathophysiology and drug repurposing. Meta-analysis of RNA-Seq datasets from COVID-19 recovered and LC patients was performed to identify altered HICs in LC. Differential gene expression analysis, functional enrichment analysis, and weighted gene co-expression network analysis (WGCNA) were performed to uncover key genes, pathways, and co-expression modules consisting of HICs, lipid metabolism-, and immune signaling-related genes. Drug-gene interaction analysis was performed to identify approved drugs targeting potential HICs. A total of 715 dysregulated genes, including eighteen HICs were identified, among which seven were potassium channels. Three significant modules containing HICs, lipid metabolism-, and immune signaling-related genes were identified and found to be associated with antigen processing and presentation, complement and coagulation cascades, and cytokine-related pathways. Approved drugs targeting KCNA6, KCNJ10, KCNN3, and KCNH4 were identified. With further experimental validation, these dysregulated potassium channels, supported by their co-expression networks and pathway associations, may act as potential candidates for drug repurposing in LC patients.

14.
arXiv (CS.CV) 2026-06-18

LARE: Low-Attention Region Encoding for Text-Image Retrieval

Image retrieval in crowded scenes is particularly challenging due to the salience bias of conventional visual encoders, which tend to focus on dominant objects while neglecting low-attention regions that are often crucial for fine-grained retrieval. We propose LARE (Low-Attention Region Encoding), a framework that explicitly models these overlooked regions. LARE adopts a dual-encoding strategy that encodes low-attention regions of an image and the full image in parallel, leading to more diverse and informative image embeddings. To evaluate image retrieval performance in challenging crowded scenes, we introduce Dense-Set, a challenging subset derived from COCO and Flickr30K. In this subset, images are re-captioned to provide richer descriptions of low-attention or previously overlooked regions. This dataset highlights the limitations of existing retrieval models and enables a more rigorous evaluation under densely crowded scene conditions. Experimental results demonstrate that the proposed framework improves retrieval performance by preserving subtle, non-dominant visual cues within the shared latent space.

15.
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.

16.
arXiv (CS.CV) 2026-06-12

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models

Vision-Language Models (VLMs) hallucinate objects that are not present, and a growing line of work tries to curb this by feeding the model its own generated caption as auxiliary evidence – assuming that a caption, once available, is something to consume. We show this fails: naively appending a caption can lower accuracy rather than raise it, dropping Qwen2.5-VL-3B$^\dagger$ on HallusionBench by nearly ten points. To understand why, we build GD-Probe, a diagnostic set that pairs a global and a detail question on the same image, so that any difference in caption effect is attributable to the question alone. Caption utility proves to be a per-query property: the same caption helps global questions and harms detail ones, through a single mechanism – an embedded caption competes with the image for attention and pulls the model's evidence onto its own text – whose sign is set by whether the caption covers the queried content. Crucially, this regime is readable from quantities the decoder already emits, with no attention access or grounding. We turn this into GEASS (Gated Evidence-Adaptive Selective Caption Trust), a training-free, logit-level module that decides per query how much of the caption to trust, gating it by the clean path's confidence, weighting it by the entropy reduction it induces, and raising the evidence bar when the two pathways disagree. Across four VLMs and two benchmarks (POPE and HallusionBench), GEASS improves over both vanilla inference and contrastive decoding under a single fixed setting, adding only two forward passes and no parameters.

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

A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents

作者:

arXiv:2606.12320v1 Announce Type: new Abstract: Enterprise security was built to govern data boundaries: the protected surface was data at rest and in transit, and the controls – access control, data-loss prevention, perimeter inspection – governed crossings of that boundary. Production AI agents dissolve this assumption. An agent reads context, calls tools, invokes connectors, and modifies systems of record on an enterprise's behalf, so risk moves inside the workflow, into sequences of individually-permitted actions that may transform a business process no one authorized. Existing policy engines do not extend to this regime: they evaluate request-time decisions against atomic principals, where agentic systems require stateful evaluation against composite principals whose authority attenuates through delegation chains. We present a reference architecture for the runtime governance of production agents, built from four composable primitives: a five-plane decomposition (a reasoning plane that adjudicates intent, and four enforcement planes – network, identity, endpoint, data – that realize the decision), stop-anywhere mediation, composite principals with capability attenuation, and audit as a structured evidence substrate. We define a taxonomy of six interruption primitives that generalize allow and deny, state and argue for four correctness invariants, and demonstrate the foreclosure of seven production-agent threats across five concrete workflows. A reference implementation of the policy-engine core supplies measured evidence: attenuation correctness and evidence reconstructability hold on every trial, adjudication runs in single-digit microseconds, and the audit substrate's tamper-evidence behaves exactly as designed. We are explicit about scope: the architecture governs delegated action, not model behavior, and a full-system evaluation against a live agent benchmark is the invited next step.

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

Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration

Knowledge Graph Question Answering (KGQA) offers grounded, interpretable reasoning, but existing methods often fail to provide reliable coverage guarantees over retrieved answers. While Conformal Prediction (CP) offers a principled framework for producing prediction sets with statistical guarantees, prior conformal KGQA methods suffer from two critical pitfalls: violated coverage guarantees due to invalid calibration, and weak score discriminability that yields excessively large prediction sets. We propose Conformal Path Reasoning (CPR), a novel trustworthy KGQA framework built on two key innovations. First, query-level conformal calibration over path-level scores preserves exchangeability to ensure valid coverage guarantees. Second, we introduce the Residual Conformal Value Network (RCVNet), a lightweight module trained via PUCT-guided exploration to learn discriminative path-level nonconformity scores. Extensive experiments show that CPR significantly improves the Empirical Coverage Rate by 45% while reducing prediction set size by 52% on average over conformal baselines across benchmark datasets, highlighting its effectiveness for reliable conformal reasoning over knowledge graphs.

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

Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning

This paper explores agentic 3D spatial understanding, i.e., MLLM agents performing 3D reasoning through tool use. Existing methods often misuse tools and exhibit biased tool preferences under 3D scenarios, leaving the agentic paradigm with only marginal gains over non-agentic strategies. We reveal that 3D spatial reasoning tasks are heterogeneous across scenes, while these agents apply a uniform tool-use strategy to all scenes rather than selecting tools according to the specific scene and task. To address this, we propose Skill-3D, a framework that learns self-evolving scene-aware skills. Specifically, Skill-3D identifies the task scene and records the agent's tool-use trajectory into a Scene Memory, where successful trajectories from similar scenes are aggregated and distilled into a reusable scene-aware skill, with failed ones attached to the skill as lessons. During training, once a similar scene recurs, the corresponding skill is injected to guide the agent, producing new trajectories whose successes and failures further refine the skill, forming a loop in which the memory and the skill library co-evolve. Experiments show that Skill-3D substantially improves tool utilization in 3D spatial reasoning (from 39% to 78% on VSI-Bench), driving the agent toward correct and sufficient tool use. For instance, it improves Gemini-3-Flash by 67% on MMSI-Bench. Furthermore, we conduct agentic post-training over skill-guided trajectories, which boosts Qwen3-VL-8B by 60% on VSI-Bench.

20.
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

21.
arXiv (CS.CV) 2026-06-19

LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation

Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentation. The immense computational requirements of backbones often necessitate distillation into smaller architectures for edge deployment. Feature-based knowledge distillation (KD) often suffers from the teacher-student gap; the student struggles to imitate teacher's complex feature map due to its limited capacity. To mitigate this bottleneck, we propose LEAP: Layer-skipping Efficiency via Adaptive Progression, a training curriculum for ViT feature-based knowledge distillation. By utilizing the teacher's intermediate feature maps as a sequence of progressively more difficult targets, our curriculum allows the student to build a foundational representation before tackling higher-level abstractions. Our results demonstrate that this paradigm significantly accelerates convergence through adaptive difficulty selection across various student model sizes and dataset scales. With our curriculum, the LEAP-distilled ViT-S achieves 90.1% accuracy on ImageNet-100, a +12.24% improvement compared with baseline. On ImageNet-1K, LEAP achieves +3.84% and +7.75% improvement for the instance retrieval task on the Oxford and Paris datasets, respectively. Furthermore, the curriculum enables 25.1% savings in training FLOPs and 21% savings in training time on ImageNet-100 by implementing early-stopping for teacher inference during the initial stages of training. Code is available at https://github.com/KevinZ0217/LEAP

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

Too long; didn't solve

arXiv:2604.07593v2 Announce Type: replace Abstract: Mathematical benchmarks consisting of a range of mathematics problems are widely used to evaluate the reasoning abilities of large language models, yet little is known about how their structural properties influence model behaviour. In this work, we investigate two structural length variables, prompt length and solution length, and analyse how they relate to model performance on a newly constructed adversarial dataset of expert-authored mathematics problems. We find that both prompt and solution lengths correlate positively with increased model failure across models. We also include a secondary, exploratory analysis of cross-model disagreement. Under a difficulty-adjusted normalised analysis, both variables retain weak negative associations with realised model separation, slightly stronger for prompt length. Overall, our main robust finding is that structural length is linked to empirical difficulty in this dataset.

23.
arXiv (CS.CV) 2026-06-24

Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective

Semi-supervised few-shot learning (SSFSL) resembles real-world applications such as auto-annotation, as it aims to learn a model from a few labeled and abundant unlabeled task-specific examples to annotate the unlabeled ones. Despite the availability of powerful open-source Vision-Language Models (VLMs) and open-world data, existing SSFSL literature largely neglects these resources. In contrast, the related area few-shot learning (FSL) has already exploited them to boost performance. Arguably, to solve real-world auto-annotation, SSFSL should leverage such open resources. To bridge this gap, we explore established SSL methods to finetune a VLM. Unexpectedly, they significantly underperform FSL baselines that do not use unlabeled data. Our in-depth analysis reveals the root cause of failure: VLMs produce flat distributions of softmax probabilities, resulting in zero utilization of unlabeled data and weak supervision signals. To address this challenge, we propose an embarrassingly simple solution that uses temperatures to sharpen the softmax output, which not only increases the confidence scores of pseudo-labels to improve the utilization of unlabeled data, but also strengthens training supervision for effective finetuning. Furthermore, we exploit task-relevant open data, e.g., those retrieved from VLMs' publicly available pretraining set. To mitigate the imbalance and domain gaps in retrieved data, we employ a stage-wise training strategy. Building on the successful finetuning of VLMs and the exploitation of open data, we present a simple yet effective SSFSL method, Stage-Wise Finetuning with Temperatures (SWIFT). Across five benchmarks, SWIFT outperforms recent FSL and SSL methods by $\sim$5 accuracy points. SWIFT even rivals supervised learning, which finetunes a VLM assuming unlabeled data having ground-truth labels!

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

Oops, Wait: Discourse Tokens Matter in Reasoning Model

Recent studies suggest that even data-efficient training with ($\simeq$1K) reasoning trajectories can induce non-trivial reasoning capabilities in large language models through post-training. Such training corpora often contain iconic tokens such as "wait", "so", and "alternatively", which frequently appear in reasoning trajectories and may play a role in this process. This paper focuses on characterizing observable token-level patterns in post-training and a case study of how data-efficient supervised fine-tuning (SFT) differs from, and falls short of, large-scale post-training. To this end, we first identify tokens that correlate with correct answers along reasoning trajectories across models and training setups. We then focus on the distribution and (functional) roles of the "wait" token to primarily study the model trained in a data-efficient manner compared with the counterpart. Our study finds that discourse tokens are associated with correctness and a reasoning accuracy jump, even in data-efficient SFT. This suggests data-efficient SFT can partially reproduce discourse-token patterns to mimic meaningful reasoning behavior, but the patterns are less aligned with high-confidence answer transitions than those from large-scale post-training.

25.
arXiv (CS.CL) 2026-06-11

DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios

Human creativity has emerged as a critical competency in the era of large language models. Assessing creativity in complex, open-ended environments is a grand challenge in data mining, currently hindered by a reliance on standardized simple tasks and the scarcity of fine-grained expert data. As an ecologically valid assessment context, debate reflects multiple dimensions of creativity, encompassing both divergent thinking and convergent thinking. Moreover, debate is a data-rich domain, with a large volume of publicly accessible materials. Current mainstream automated scoring methods are poorly suited to complex settings such as debate, and therefore still rely on costly human evaluation. To this end, this paper proposes DEFINED, a data-efficient computational framework for fine-grained creativity assessment in debate scenarios. DEFINED operationalizes debate creativity through a hierarchical eight-dimensional metric system, implemented via a pre-trained autoregressive language model with a hierarchical scoring head that supports both fine-grained and coarse-grained evaluation. Statements and their associated expert scores were obtained from authentic debate competitions, and a constrained data augmentation strategy was employed to address the elite bias inherent in the original data. DEFINED adopts a mixed-granularity training strategy enabling robust learning from limited fine-grained supervision annotated by trained graduate experts. To rigorously validate ecological validity beyond synthetic benchmarks, we incorporate an empirical study with debate-naive participants, utilizing these authentic data to serve as a qualitative case study for mid-to-low proficiency populations. Across our evaluation protocol, our scoring model achieves accurate and stable scoring, outperforming prompt-based large language model evaluators and existing debate scoring methods.