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) 2026-06-17

Coherent Control of an Embedded Bound State Without a Spectral Gap

作者:

arXiv:2606.17685v1 Announce Type: new Abstract: Bound states in the continuum (BICs) can confine photonic excitations in open systems without conventional cavities or band gaps, making them natural candidates for long-lived quantum storage and single-photon control. Their use is limited, however, by two obstacles: they are dark to incident photons, and they lack spectral-gap protection from the surrounding continuum. We overcome both limitations in a giant atom coupled to a one-dimensional waveguide using two temporal control knobs. Atomic-frequency modulation breaks and restores the destructive-interference condition, enabling deterministic capture and release of mode-matched single photons. Coupling modulation instead preserves the BIC condition while tuning the atomic and photonic weights of the stored state. A key result is that this embedded state can nevertheless be controlled adiabatically despite the absence of a spectral gap, with an intrinsic leakage probability linear in the ramp rate. By separating radiative access from BIC-preserving deformation, the protocol turns a dark BIC into a single-photon memory whose fidelity is set by the intrinsic continuum-induced leakage law, providing a route to embedded-state control in open photonic platforms.

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

Physics-Informed Neural Network with Squeeze-Excitation-like Attention

arXiv:2606.19853v1 Announce Type: new Abstract: We introduce SEA-PINN, a novel architecture that incorporates a Squeeze-Excitation-like attention mechanism into physics-informed neural networks to dynamically recalibrate the importance of neurons across layers. A key feature of SEA-PINN is its highly stable initialization. On 17 out of 20 benchmark problems, SEA-PINN exhibit nearly negligible variance and significantly reduced initial loss, establishing a quasi-deterministic and favorable starting point for optimization. Notably, without employing Fourier feature embeddings or periodic activation functions, SEA-PINN attained competitive accuracy (83\% vs. 90\% improvement relative to FNN-PINN on the high-frequency case 7) as compared with TSA-PINN-a model specifically engineered for high-frequency problems via learnable frequencies in sinusoidal activations. Furthermore, integrating SEA-PINN into TSA-PINN boosted performance by 42.49\%. These results underscore SEA-PINN as a lightweight plug-in module that enhances nonlinear representation power, promotes more robust and efficient convergence, and strengthens the overall reliability of physics-informed learning.

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

Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations

Multimodal large language models (MLLMs) excel at visual reasoning but rely on text-based chain-of-thought (CoT), lacking interpretable visual intermediates. Existing methods use opaque tokens or external tools, missing key properties. We propose Gen-VCoT, a framework using expert vision models to generate RGB images as reasoning intermediates. It has three stages: visual grounding (SAM segmentation), geometric reasoning (Marigold depth maps), and semantic reasoning (Qwen2-VL integration). An adaptive router selects reasoning depth. Evaluations show Gen-VCoT improves spatial (25% better) and depth (50% better) questions, but may hurt simple factual queries. Text CoT outperforms visual intermediates on CLEVR (91.2% vs 62.5%), showing task-dependent optimal representations. Gen-VCoT establishes a new paradigm for interpretable multimodal reasoning.

04.
arXiv (CS.CL) 2026-06-11

Agreement in Representation Space for Open-Ended Self-Consistency

Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on exact matching and therefore remain limited to tasks with categorical outputs. In this work, we study self-consistency in open-ended generation tasks such as code synthesis and text summarization. We hypothesize that consistency can be understood as a geometric property of the generation space, where semantically compatible generations concentrate in similar regions of representation space. To study this hypothesis, we introduce Embedding-Based Agreement (EBA), a simple training-free operationalization that estimates agreement by clustering sampled generations in embedding space. Through experiments on mathematical reasoning, code generation, and summarization, we show that agreement in representation space provides a robust and scalable signal of self-consistency for open-ended tasks. In particular, EBA consistently outperforms random selection and exhibits more stable scaling behavior than recent selection approaches based on LLM evaluation or uncertainty estimation. We further show that these agreement signals remain stable across model families and embedding spaces, even with native hidden representations. Finally, our analysis shows that the geometric location occupied by sampled generations is strongly correlated with generation quality: generations concentrated near central regions of representation space tend to correspond to more reliable outputs, whereas peripheral generations are substantially less accurate. Overall, our findings support viewing self-consistency as a property of the geometric organization of sampled generations rather than exact symbolic overlap.

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

A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development

arXiv:2606.14816v1 Announce Type: cross Abstract: This paper presents a structured analysis of security challenges in long-horizon agentic AI systems. The study reviews existing threats, evaluation approaches, attack propagation mechanisms, and security frameworks. A taxonomy of security threats and a framework for analyzing attack propagation are proposed to support future research in agentic AI security

06.
arXiv (quant-ph) 2026-06-15

Digital programming of spin correlations in a fermionic lattice quantum simulator

arXiv:2606.13772v1 Announce Type: cross Abstract: Analog quantum simulation provides a highly controlled platform to study diverse quantum many-body phenomena. However, current methods for state initialisation are limited to thermal ensembles or uncorrelated product states. Here we present a hybrid approach that complements analog preparation with a digital quantum-gate protocol. This approach enables the engineering of target states with specific, long-range spin-correlations from the same initial resource state. By applying collisional gates to adiabatically prepared and filtered four-fermion singlet chains, we program diverse spin-correlation patterns, including that of a Heisenberg chain. We measure the spin correlations using a sequence of quantum gates followed by singlet-pair measurements. Our method paves the way to the targeted preparation of strongly correlated states of matter.

07.
arXiv (CS.CL) 2026-06-11

ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defenses that mix logits from a safe anchor model require both models to share a vocabulary, which rules them out for the cross-family specialists where safety is most degraded. We present ALIGNBEAM, a training-free method that lifts this restriction by translating anchor logits into the target model's vocabulary token-by-token at each decoding step; a small LLM judge then selects the safest among K candidate continuations. No weights are changed, and the safety-utility trade-off can be tuned at deployment without retraining. Across both cross-vocabulary and same-vocabulary evaluation pairs, ALIGNBEAM substantially raises refusal on adversarial benchmarks while keeping task accuracy and inference overhead within practical bounds. The results show that safety alignment can be transferred between model families at inference time, without touching either model's weights.

08.
arXiv (CS.CV) 2026-06-11

From Simulation to Real-World: An In-Field 6D Pose Dataset and Baseline for Robotic Strawberry Harvesting

Robotic strawberry harvesting requires precise 6D pose estimation; however, collecting 6D pose ground truth in real agricultural fields is inherently challenging. Existing 6D pose estimation methods have therefore relied solely on synthetic data that lacks scene-level realism, leaving their performance under real agricultural field conditions unquantified. In this work, we present, to the best of our knowledge, the first real-world 6D pose ground truth dataset of strawberries collected in actual agricultural fields (12,040 images). We also introduce a synthetic dataset rendered in NVIDIA Isaac Sim, featuring scene-level realism and domain randomization. Nevertheless, our experiments reveal that a significant sim-to-real gap persists, underscoring the necessity of real agricultural field data for reliable evaluation. We further quantify the sim-to-real gap through baseline 6D pose estimation results across backbone encoders, serving as a reference for future work. The real-world dataset will be made available upon acceptance.

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

Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelines for Safety Enforcement at Scale

Safety classifiers that screen LLM inputs for jailbreak attempts have become standard deployment components, yet almost all production systems rely on GPU-based models: fine-tuned transformers and LLM-as-a-judge pipelines. These approaches impose significant per-query latency and infrastructure cost. Very little research has asked whether CPU-based classifiers, such as support vector machines and gradient-boosted trees trained on TF-IDF features, can match their accuracy across the conditions that production deployments encounter. We evaluate five CPU classifier families, Mamba-130M as an SSM-based GPU classifier, and transformer-based GPU models (DeBERTa-v3 and Gemma-2B with LoRA) across nine jailbreak sources and three regimes: in-distribution (D1), out-of-distribution (D2), and adversarially obfuscated (D3). On D1, the best CPU classifier matches the best transformer GPU model at roughly one-fifth the deployment cost. On D2, CPU classifiers fail via confident miscalibration, producing high-confidence false negatives that bypass escalation entirely. On D3, CPU classifiers outperform transformer GPU models by more than 26 percentage points in F1. Based on these complementary failure modes, we design GuardChain, a three-stage safety pipeline (Regex -> CPU -> GPU) that routes each prompt to the cheapest stage capable of a confident decision. The CPU stage alone resolves 80\% of in-distribution prompts at near-peak accuracy, and the GPU stage recovers the out-of-distribution failures. For practitioners deploying LLM safety at scale, this work provides evidence that GPU-class infrastructure is unnecessary for the majority of traffic.

10.
arXiv (CS.CL) 2026-06-19

Where Does Social Reasoning Come From? Capability Provenance in Language Models

We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social-reasoning versus STEM-reasoning in OLMo3-7B. Training-data attribution measures how strongly each training document influences a model's predictions on a benchmark, but document-level scores are too noisy to identify which corpus regions support which capabilities, and prior work has emphasized factual knowledge rather than reasoning. We compute gradient-based attribution (TrackStar via Bergson) over a working set drawn from the de-duplicated Dolma3 mix, aggregate influence across WebOrganizer's 24-format x 24-topic taxonomy (576 bins), and contrast benchmark pairs in a 2x2 design that varies domain (social vs. STEM) and capability type (reasoning vs. knowledge): SocialIQA and MMLU Social Sciences against ARC-Challenge and MMLU STEM. Social and STEM reasoning draw on qualitatively distinct corpus regions, and the contrast is sharper at the reasoning level than at the knowledge level. Targeted machine unlearning provides partial causal validation: forgetting high-attribution topic bins (e.g., Literature for SocialIQA) degrades the aligned benchmark more than within-bin random baselines, and we open-source all code, sampling manifests, the bin-level influence matrix, and unlearning checkpoints.

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

Echoes of the Prior: A Computational Phenomenology of Forgetting

Memory is not merely the storage of data; it is the scaffolding of reality. When biological memory fades, the world does not simply turn black; it regresses into an unrecognizable chaos. Echoes of the Prior is an interactive installation that attempts to visualize this subjective phenomenology of forgetting. By inducing controlled synaptic decay within a Feed-Forward 3D Reconstruction model, we create an artistic analogy for the erosion of the brain's predictive priors. We position the Neural Network not as a tool for engineering, but as a cognitive proxy - a silicon brain whose structural degeneration evokes the disorienting, poetic, and terrifying experience of losing one's grip on the world. Ultimately, we offer this framework as a catalyst, inviting the wider community to explore the uncharted potential of neuromorphic aesthetics in visualizing the fragility of intelligence. Interactive demo see https://decart-4d.github.io/.

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

Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs

Automatic Speech Recognition (ASR) has become a key technology for human–AI interaction. However, code-switching ASR (CS-ASR) remains particularly challenging due to the severe scarcity of multilingual CS speech resources across diverse language pairs. Existing approaches primarily improve CS-ASR performance through synthetic CS speech generation or pair-specific fine-tuning on limited bilingual datasets. Nevertheless, these approaches face an inherent scalability limitation, as support for CS must be developed separately for language pairs whose number grows combinatorially with the number of supported languages. In this work, we investigate whether CS capabilities learned from a limited set of seen language pairs can generalize to unseen language pairs through model merging and domain generalization methods. Our experiments show that merged bilingual CS-ASR models modestly generalize to unseen language pairs, suggesting limited transfer of bilingual CS capabilities across language pairs.

13.
arXiv (CS.CL) 2026-06-12

ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages

Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic languages and rely on multimodal inputs such as medical images. Existing English-centric MLLMs struggle to support such use cases, limiting equitable access to AI-driven healthcare assistance. To address this challenge, we introduce ArogyaBodha, a large-scale multilingual multimodal medical question-answer dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains across English and seven major Indian languages. We further propose ArogyaSutra, an actor-critic-based multi-agent framework that integrates tool grounding with dual-memory mechanisms for step-wise, reasoning-aware decision making, and uses stored actor-critic simulation trajectories for distillation. Experiments show that our dataset and framework improve multilingual medical reasoning accuracy across all Indic languages, with ablations validating the contribution of each component. The source code and dataset are available at: https://iitp-cse.github.io/ ArogyaSutra/

14.
arXiv (quant-ph) 2026-06-11

Exact Dynamics of Topological Order Across a CDW–SPT Transition

arXiv:2606.11303v1 Announce Type: cross Abstract: We investigate the nonequilibrium dynamics of a one-dimensional interacting system across a transition from a charge-density-wave (CDW) phase to a symmetry-protected topological (SPT) phase. Starting from a CDW initial state, we study both sudden quenches and slow ramps into the SPT regime. While the CDW order melts under both protocols, the fate of topological order is sharply different. Following a sudden quench, long-range SPT order does not emerge because the post-quench state contains a finite density of excitations above the topological ground state. In contrast, slow ramps allow the system to follow the instantaneous ground state away from the critical region, enabling the buildup of SPT order with deviations governed by Kibble-Zurek defect production. The dynamics is solvable via a unitary mapping to a quadratic fermionic Hamiltonian, allowing us to compute the Loschmidt echo, correlation functions, and string correlator. The Loschmidt rate function exhibits cusps signaling dynamical quantum phase transitions, while the correlation dynamics reveal the contrasting mechanisms governing quenches and ramps across the transition. These results demonstrate that entering the topological regime is not sufficient for the emergence of topological order; the decisive factor is the suppression of excitation production during the evolution.

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

Arbitrary control over multimode wave propagation for machine learning

arXiv:2402.17750v2 Announce Type: replace-cross Abstract: Controlled multimode wave propagation can enable more space-efficient photonic processors than architectures based on discrete components connected by single-mode waveguides. Instead of defining discrete elements, one can sculpt the continuous substrate of a photonic processor to perform computations through multimode interference in two dimensions. Here we designed and demonstrated a device with a refractive index that can be rapidly reprogrammed across space, allowing arbitrary control of wave propagation. The device, a two-dimensional programmable waveguide, uses parallel electro-optic modulation of the refractive index of a slab waveguide with about $10^4$ programmable spatial degrees of freedom. We implemented neural network inference on benchmark tasks with up to $49$-dimensional vectors in a single pass, without digital pre-processing or post-processing. Theoretical and numerical analyses further indicated that two-dimensional programmable waveguides may offer not only a constant-factor reduction in device area but also a scaling benefit, with the area required growing as $N^{1.5}$ rather than $N^2$.

16.
Nature (Science) 2026-06-09

How ice forms is a mystery — now scientists are cracking the case

Theories about how ice crystals grow in cooling liquids are wildly inaccurate when compared with experimental data, but studies are starting to illuminate the earliest moments in freezing. Theories about how ice crystals grow in cooling liquids are wildly inaccurate when compared with experimental data, but studies are starting to illuminate the earliest moments in freezing.

17.
arXiv (quant-ph) 2026-06-11

Handbook of Error-Correcting Codes

arXiv:2606.11484v1 Announce Type: new Abstract: Barcode scans, clear phone calls, reliable data storage, satellite communication, and large-scale quantum computation are all made possible by error correction. We present a handbook version of The Error Correction Zoo, a curated reference of methods for protecting classical or quantum information from errors during storage and transmission. The handbook includes descriptions of these error-correcting codes and a classification according to the symbols they use. It also catalogues relations among codes and related objects such as sphere packings, lattices, designs, groups, and classical and quantum phases of matter. The collection is intended both as a rigorous reference and as a practical aid for tracing the web of code relationships and uncovering new connections.

18.
arXiv (quant-ph) 2026-06-12

Beyond-Third-Order Quantum Coherence in Two-Dimensional Spectroscopy via Order-Selective Isolation

arXiv:2606.12794v1 Announce Type: new Abstract: A central challenge in nonlinear spectroscopy is the order-selective readout of weak higher-order responses that spectrally overlap with dominant lower-order signals. This bottleneck is particularly severe in two-dimensional (2D) spectroscopy, where extending conventional phase-cycling schemes to higher orders rapidly increases measurement and analysis complexity. Here we introduce a computation-assisted strategy that combines rotating-frame acquisition with a frame-shift tracking algorithm to separate signals by their frame-dependent spectral shifts. In a rubidium vapor experiment, we use this approach to isolate a 7th-order nonlinear contribution from coexisting 3rd-order components, enabling direct access to higher-order quantum-coherence dynamics without sacrificing operation at comparatively high pulse intensities. The method is broadly compatible with multidimensional spectroscopy platforms and provides a practical route to probing many-body and collective ultrafast dynamics beyond third order.

19.
arXiv (CS.CL) 2026-06-19

CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference

Retrieval-Augmented Generation (RAG) improves factual grounding, but it also lengthens prompts and raises prefill cost. Prefix caching in serving engines such as vLLM reduces this cost only when requests share the same token prefix. In grounded generation, however, adjacent queries may retrieve overlapping evidence in different orders, so set overlap does not become reusable prefix overlap. We present CacheWeaver, a lightweight prompt-layer method for cache-aware evidence ordering. The method keeps a prefix tree over recently served evidence sequences and uses a greedy walk to place the most reusable prefix first, while leaving the serving engine and retrieved evidence set unchanged. Across three vLLM configurations, the method lowers median time-to-first-token (TTFT) by about 20-33 percent relative to retrieval-order prefix caching, without hurting answer quality in our QA tests. The greedy policy reaches 97.5 percent of the median TTFT gain from oracle ordering, indicating that most reusable prefix locality can be recovered by a simple scheduling layer between retrieval and inference.

20.
arXiv (CS.CL) 2026-06-11

Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness

End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present layer-isolated evaluation: a deployed ordering agent is decomposed into a fixed taxonomy of layers (ontology, intent, routing, decomposition, escalation, safety, memory, and cross-cutting envelope/defense), each exercised by its own assertion slice in a deterministic, no-LLM "pure" mode. The pure suite (238 cases across 23 slices; 225 run in 2.39 s, ~10 ms/case) runs in CI on every change against a locked per-slice baseline. We validate by controlled regression injection, degrading one layer at a time across seven non-safety layers. The effect we did not design in is masking: the aggregate pass-rate barely moves (-1.7 to -5.9 pp for six local regressions), while the matching slice craters (-25 to -91 pp). A layer's slice reacting to its own fault is partly by construction; the measured results are (i) the aggregate masking and (ii) that damage stays off the other slices: the injected layer's slice is the single worst-hit in 5 of 7 cases and top-3 in 7 of 7 (mean rank 1.29 of 19). Localization replicates on a second, structurally different tenant (Starbucks SG): all seven matching slices crater, so it is not a single-catalog artifact. We position it as a concrete, deterministic instantiation of the component-level evaluation EDDOps prescribes but leaves unimplemented, with CheckList as ancestor and as the deterministic mirror image of whole-workflow stochastic mutation testing. Our contributions: (a) a fully decomposed, sub-second, no-LLM per-layer harness for a production agent, (b) a coverage-honesty test-adequacy criterion that refuses to score an unexercised layer, and (c) the regression-injection demonstration that per-slice baseline-locked gates localize regressions an aggregate metric masks.

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

Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models

arXiv:2606.19635v1 Announce Type: cross Abstract: Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these transformer-based architectures effectively and efficiently remains a major challenge. Conventional approaches that "textualize" these signals directly or create discrete item representations often lead to excessively long prompts, substantial memory footprints, and high computational overhead. To overcome these limitations, we propose "Token Factory", a framework designed to transform traditional signals into "soft tokens" that can be directly processed by LRMs. This approach enables efficient integration and compression of heterogeneous input features, preventing prompt length explosion while enhancing model performance. We detail the architecture of Token Factory and present experimental results validating its effectiveness in a production-scale recommendation environment.

22.
arXiv (CS.AI) 2026-06-12

Variational Learning for Insertion-based Generation

arXiv:2606.02133v3 Announce Type: replace-cross Abstract: Non-monotonic sequence generation methods, such as masked diffusion models, provide a flexible alternative to left-to-right autoregressive modeling by allowing tokens to be generated in non-fixed and prescribed orders. Despite their practical advantages, most existing non-monotonic models are order-agnostic and rely on a fixed-length grid, limiting their ability to support variable-length generation and adaptive insertion order. In this work, we introduce a probabilistic framework for learning insertion order in variable-length insertion models. We formalize a bijective correspondence between insertion trajectories and permutations, which enables an exact reparameterization of the data likelihood as a sum over permutations. Building on this result, we propose the Insertion Process (IP), a stochastic generative model that jointly learns where to insert, what to insert, and when to terminate, trained via permutation-based variational inference. Unlike prior fixed-canvas approaches, IP natively supports variable-length generation and learns data-driven preferences over insertion orders. Experiments on goal-conditioned planning and molecular string generation demonstrate that learning insertion order improves both modeling quality and generalization in domains without a canonical left-to-right structure.

23.
arXiv (CS.AI) 2026-06-19

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns

arXiv:2606.19613v1 Announce Type: cross Abstract: We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

24.
arXiv (CS.AI) 2026-06-11

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

arXiv:2606.09426v2 Announce Type: replace Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchmarks, however, often evaluate these interfaces as separable capabilities, leaving long-horizon cross-interface orchestration under-tested. Thus, we introduce WeaveBench, a long-horizon hybrid-interface benchmark with 114 tasks across 8 real-world work domains, grounded in real user requests and publicly verifiable artifacts. Each task requires agents to combine GUI observations/actions with CLI/code operations within a single trajectory. We evaluate these tasks on a real Ubuntu desktop inside deployed CLI-agent runtimes, augmented with a minimal desktop-control plugin. We also propose a companion trajectory-aware judge that inspects deliverables, files, screenshots, logs, and action traces, while detecting shortcut behaviors such as fabricated visual evidence or hard-coded metrics. Across frontier model-runtime pairings, the best PassRate reaches only 41.2%, showing the benchmark remains far from saturated. The trajectory-aware judge further reveals that outcome-only grading substantially overestimates agent performance. Overall, WeaveBench exposes a critical gap in CUA evaluation and provides an effective testbed to measure whether agents can orchestrate GUI, CLI, and code operations across long-horizon real-world tasks.

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

Koshur Diacritizer: A Byte-Level Sequence-to-Sequence Model for Kashmiri Diacritic Restoration

Kashmiri, an Indo-Aryan language written in a modified Perso-Arabic script, frequently omits diacritic marks in digital text, creating ambiguity and challenging downstream NLP applications. We present Koshur Diacritizer, a ByT5-small byte-level sequence-to-sequence model for restoring diacritics in Kashmiri text. To support this task, we release a publicly available dataset of 23.7k aligned undiacritized diacritized Kashmiri sentence pairs. The proposed framework combines script-aware normalization, alignment validation, and skeleton-preserving inference to ensure reliable restoration while maintaining the original base-letter sequence. Experimental results on a held-out test set achieve a DERm of 0.2012 and a WER of 0.2159. Additionally, evaluation by a native Kashmiri linguistic expert yields a mean accuracy of 77.5%. The dataset, model, and source code are publicly released to provide a reproducible baseline for Kashmiri diacritic restoration and future low-resource language research.