中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
02.
arXiv (CS.AI) 2026-06-16

Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs

Authors:
Jierui Zhang↗Siyuan Tan↗Xinhang Li↗Longzhuangzhi Lin↗Dailin Li↗Chengfeng Gu↗Xinping Li↗Yaxian Hao↗Shengjia Liang↗Yuxiang Ren↗Wenhao Liu↗

arXiv:2606.15258v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs across diverse sources. This evaluation gap limits trustworthy AI assistance in proof-certified scientific progress. Existing evaluations often emphasize final answers or rely on costly expert grading, while end-to-end proof generation remains open-ended and hard to verify automatically. We introduce Mask-Proof, a pipeline that turns real proofs into automatically checkable masked-step tasks. It masks key formula steps, provides the necessary surrounding context, and evaluates model reconstructions with an LLM-based equivalence judge using repeated votes for stability. The resulting Mask-ProofBench contains 292 curated problems across diverse research areas. Experiments with 17 models show that reasoning-enhanced models outperform standard models by 12% to 27%. Our evaluator achieves 96.8% agreement with expert annotators, enabling faithful, reproducible, and comparable measurement of step-level mathematical reasoning. Benchmark, annotations, and code are available at https://github.com/weating/Mask-Proof.

Read & Discuss → View Source →
03.
arXiv (CS.AI) 2026-06-16

Guiding Federated Graph Recommendation with LLM-encoded knowledge

Authors:
Thi Minh Chau Nguyen↗Hien Trang Nguyen↗Duc Anh Nguyen↗Van Ho-Long↗Thanh Trung Huynh↗Zhao Ren↗

arXiv:2606.15277v1 Announce Type: cross Abstract: Graph-based recommender systems are highly effective at extracting collaborative signals from user–item interactions, and federated learning (FL) allows these models to be trained while preserving user privacy. However, aggregating graph representations across distributed, non-IID clients remains a challenge; structural embeddings learned locally often misalign, and naive averaging fails to capture meaningful cross-client relationships. Most existing federated graph methods rely exclusively on structural aggregation, neglecting the rich, global semantic context available in large language models (LLMs). In this paper, we propose a novel framework that uses LLM-encoded knowledge to guide federated graph recommendation. Specifically, clients learn structural representations from local graphs while simultaneously summarizing their typical interaction patterns into compact semantic vectors via a frozen LLM. The central server then uses these LLM-encoded semantic signals to discover related preference patterns across clients, guiding the selective aggregation of their structural representations. This enables semantically informed cross-client collaboration without exposing raw data. Extensive experiments on standard benchmarks show that guiding structural alignment with LLM-encoded knowledge consistently improves recommendation accuracy over existing federated graph baselines.

Read & Discuss → View Source →
04.
arXiv (CS.CL) 2026-06-12

Small LLMs for Biomedical Claim Verification: Cost-Effective Fine-Tuning, Structural Dataset Shortcuts, and Cross-Domain Generalization

Authors:
Gaurav Kumar↗

Large Language Models such as GPT-4o and GPT-5 achieve strong zero-shot performance on biomedical claim verification, but cost and opacity limit scalable use. We fine-tune three small LLMs: Phi-3-mini (3.8B), Qwen2.5-3B, and Mistral-7B, via QLoRA on SciFact and HealthVer, providing the first study of QLoRA models against GPT-4o and fine-tuned BioLinkBERT encoders. Mistral-7B QLoRA surpasses both GPT-4o and GPT-5 (up to 12% F1 gain) at a fractional cost using just 1,008 training examples. We conduct extensive in-domain and cross-domain evaluation: models trained on SciFact tested on HealthVer and vice versa, at matched sizes to isolate dataset structure from data quantity. We identify a previously unreported structural artifact in SciFact that inflates in-domain scores, and show through bidirectional out-of-domain evaluation that training on structurally sound data enables robust cross-domain transfer. We plan to release all code and adapter checkpoints.

Read & Discuss → View Source →
05.
arXiv (CS.CL) 2026-06-16

A Self Consistency Based Reranking for Narrative Question Answering

Authors:
Molham Mohamed↗Ali Hamdi↗

Narrative question answering (NQA) is a challenging task in natural language processing that requires models to understand long textual contexts, capture relationships across events, and generate coherent responses. Despite recent advances in pretrained language models, most existing approaches rely on a single decoding output during inference, making them sensitive to generation variability and often resulting in incomplete or inconsistent answers .To address this limitation, we propose a self-ensemble Self-Consistency-Based reranking framework for narrative question answering. The proposed method generates multiple candidate answers for each story-question pair and selects the final answer based on semantic agreement among the generated responses. This allows the model to explore diverse answer formulations while improving robustness through consensus-based selection without requiring modifications to the underlying architecture .The framework combines pretrained and fine-tuned language generation with multi-answer inference and similarity-based reranking. We evaluate the proposed approach on the NarrativeQA dataset using multiple models, including FLAN-T5 (Base and Small) and Pegasus-Large, under both baseline and fine-tuned settings .Experimental results demonstrate that the proposed method consistently improves performance across all models. In particular, FLAN-T5-Base achieves the best overall performance, improving from 82.32% to 86.66% (+4.34%) when combined with self-ensemble inference. Additionally, the largest improvement is observed with Pegasus-Large, which increases from 72.50% to 87.07% (+14.57%), highlighting the effectiveness of the proposed strategy.

Read & Discuss → View Source →
06.
arXiv (CS.CL) 2026-06-11

Improving Cross-Format Robustness in Language Models with Multi-Format Training

Authors:
June M. Liu↗Shaomian Zheng↗He Cao↗Dingnan Jin↗Qing Cui↗Jun Zhou↗

Large language models often remain sensitive to answer format: a question solved correctly in one form may fail in another semantically equivalent form. To study this gap, we define cross-format robustness as the extent to which a model answers the same underlying question consistently across formats. We then compare full-format training with FormatMix, which expands only a subset of training items into multiple equivalent formats using either random or targeted selection. Across GLM4 and Llama-3.1, multi-format supervision consistently improves both task performance and cross-format robustness, whereas Multiple-choice question (MCQ)-only supervision alone brings little benefit and can even reduce robustness. We further find that expanding only about 30% of the training set into multiple formats often recovers most of the gain from full-format training, and this effect appears across the model families and sizes we study. These results suggest that format diversity, rather than additional supervision alone, is the key driver of robustness. That lightweight multi-format augmentation is a practical way to make LLMs less sensitive to answer format without changing the base model.

Read & Discuss → View Source →
07.
arXiv (CS.CV) 2026-06-12

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

Authors:
Guozhen Zhang↗Xuerui Qiu↗Yutao Cui↗Tianhui Song↗Changlin Li↗Junzhe Li↗Tao Huang↗Xiao Zhang↗Yang Li↗Jianbing Wu↗Miles Yang↗Zhao Zhong↗…

Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDRA-X, the first UMM that unifies image and video tokenization within a single Vision Transformer (ViT). Our design is driven by two core challenges: efficiently injecting spatiotemporal reconstruction capability into a native ViT, and embedding image- and video-level semantic awareness into the latent space. To address the first, comprehensive ablations reveal two key findings: (1) frame-level causal temporal attention suffices for visual reconstruction, whereas full spatiotemporal attention degrades it; and (2) hierarchical temporal compression substantially outperforms single-step alternatives. To tackle the second, we propose a lightweight decompressor that upsamples temporally compressed features under joint image-video teacher supervision, thereby enforcing complementary semantic structures within the compact latent space. Building on this holistic tokenizer, we further propose a principled improvement of the editing pipeline: source-target interaction should occur at the latent level inside the tokenizer rather than at the semantic level inside the LLM, substantially improving editing consistency and accelerating convergence. Instantiated at the 7B dense model, HYDRA-X achieves strong performance across image and video understanding and generation tasks, paving the way for future unified-tokenizer UMMs.

Read & Discuss → View Source →
08.
arXiv (CS.CL) 2026-06-16

Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning

Authors:
Reef Menaged↗Gili Lior↗Shauli Ravfogel↗Roee Aharoni↗Gabriel Stanovsky↗

We propose agentic automata learning to evaluate the extent to which tool-calling LLM agents can uncover hidden environments through interaction. In our setup, an agent should uncover a hidden deterministic finite automaton (DFA) by interacting with an oracle through (1) membership queries ("Does this string belong to the target language?") and (2) equivalence queries ("Is this the target DFA?"). This yields a scalable testbed with controlled task complexity, measurable interaction efficiency, and strong baselines (classic automata-learning algorithms). Evaluating state-of-the-art LLMs, we find that performance drops sharply as DFA size increases. Reasoning models are markedly stronger than non-reasoning models, yet trajectory analyses reveal recurring failures in query planning, evidence integration, and hypothesis construction. Overall, our results show that current LLM agents can sometimes perform non-trivial interactive discovery, but remain far less robust and efficient than classic algorithms for the task.

Read & Discuss → View Source →
09.
bioRxiv (Bioinfo) 2026-06-11

An AI-Powered Trisomy 21 Research Assistant

Authors:
NANDI↗Sundararajan↗Subirana-Granes↗Espinosa↗J. M↗Pividori↗Sullivan↗K. D↗Galbraith↗M. D↗Costello↗

Down syndrome, caused by trisomy 21, increases the risk of diverse co-occurring conditions. With more than 34,000 related publications indexed in PubMed as of early 2026, keeping pace with this expanding literature is challenging. While general-purpose large language models are widely used for information retrieval, they often rely on broad training data rather than specific evidence. Retrieval-augmented generation (RAG) improves rigor and reliability of responses by linking model outputs to source texts. In research, source texts are peer-reviewed articles. Standard implementations treat all manuscript sections equally, allowing background text to rank as highly as experimental results. To focus model outputs on experimentally supported responses, we developed the T21 Research Assistant, a section-aware RAG system that prioritizes Results sections to ground responses in primary experimental evidence. The system draws exclusively from 1,789 open-access Down syndrome publications from PubMed Central, including 327 NIH INCLUDE-funded studies, and uses a multistage pipeline for query validation, retrieval, reranking, synthesis, and citation verification. Built on NVIDIA Nemotron models, it generates structured, cited responses. Evaluation using expert-curated questions demonstrated strong performance, achieving a BERTScore F1 of 0.712 and recall of 0.758, comparable to or exceeding leading proprietary and open-source models. T21 Research Assistant is available at: https://bioinformatics.cuanschutz.edu/t21-res-assi/

Read & Discuss → View Source →
10.
arXiv (CS.CL) 2026-06-15

Residual Context Diffusion Language Models

Authors:
Yuezhou Hu↗Harman Singh↗Monishwaran Maheswaran↗Haocheng Xi↗Coleman Hooper↗Jintao Zhang↗Aditya Tomar↗Michael W. Mahoney↗Sewon Min↗Mehrdad Farajtabar↗Kurt Keutzer↗Amir Gholami↗…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel. However, state-of-the-art block-wise dLLMs rely on a "remasking" mechanism that decodes only the most confident tokens and discards the rest, effectively wasting computation. We demonstrate that recycling computation from the discarded tokens is beneficial, as these tokens retain contextual information useful for subsequent decoding iterations. In light of this, we propose Residual Context Diffusion (RCD), a module that converts these discarded token representations into contextual residuals and injects them back for the next denoising step. RCD uses a decoupled two-stage training pipeline to bypass the memory bottlenecks associated with backpropagation. We validate our method on both long CoT reasoning (SDAR) and short CoT instruction following (LLaDA) models. We demonstrate that a standard dLLM can be efficiently converted to the RCD paradigm with merely ~300 million tokens. RCD consistently improves frontier dLLMs by 4-11 percentage points in accuracy with minimal extra computation overhead across a wide range of benchmarks. Notably, on the most challenging AIME tasks, RCD nearly doubles baseline accuracy and attains up to 4-5x fewer denoising steps at baseline's peak accuracy.

Read & Discuss → View Source →
11.
arXiv (CS.LG) 2026-06-19

Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones

Authors:
Romain Poletti↗Lorenzo Schena↗Lilla Koloszar↗Joris Degroote↗Miguel Alfonso Mendez↗

arXiv:2505.18201v2 Announce Type: replace-cross Abstract: Controlling flapping-wing drones requires controllers that handle time-varying, nonlinear, underactuated dynamics from incomplete, noisy sensor data. Recent advances in artificial intelligence (AI), particularly reinforcement learning (RL), have opened new perspectives for addressing such complex control problems through data-driven policy optimization from interaction with the environment. Yet purely data-driven methods are sample-inefficient, demanding extensive, sometimes unsafe exploration, especially without guiding physical models. This motivates hybrid AI-physics frameworks. This article proposes a hybrid model-free/model-based flight-control approach using the reinforcement twinning algorithm. The model-based (MB) component uses an adjoint formulation and an adaptive digital twin continuously identified from live trajectories; the model-free (MF) component uses RL. The two agents share knowledge via transfer learning, imitation learning, and shared experience between the real environment and the digital twin, coordinated by a policy referee that selects which agent acts in reality based on digital-twin performance and a real-to-virtual consistency ratio. The framework is evaluated for the longitudinal control of a flapping-wing drone, modelled as a nonlinear time-varying system driven by quasi-steady aerodynamic forces. The hybrid strategy is tested under three adaptive-model initializations: (1) offline identification from existing data, (2) random initialization with fully online identification, and (3) offline pre-training with biased parameters followed by online adaptation. In all cases, the hybrid framework improves performance, robustness, and sample efficiency over purely model-free and purely model-based approaches.

Read & Discuss → View Source →
12.
arXiv (CS.CL) 2026-06-16

A Unified Definition of Hallucination: It's The World Model, Stupid!

Authors:
Emmy Liu↗Varun Gangal↗Chelsea Zou↗Michael Yu↗Xiaoqi Huang↗Alex Chang↗Zhuofu Tao↗Karan Singh↗Sachin Kumar↗Steven Y. Feng↗

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we also connect our framework to HalluWorld, a complementary benchmark that instantiates fully specified reference world models for stress-testing model hallucinations.

Read & Discuss → View Source →
13.
arXiv (CS.CV) 2026-06-12

RGB-S: Image-Aligned Tactile Saliency for Robust Dexterous Manipulation

Authors:
Shengcheng Luo↗Kefei Wu↗Xiaoying Zhou↗Wanlin Li↗Ziyuan Jiao↗Chenxi Xiao↗

Effective visuo-tactile integration is critical for robotic dexterous manipulation, especially when visual observations are unreliable or occluded. However, robustly aligning sparse, heterogeneous tactile measurements with dense visual representations remains a fundamental challenge. Most existing approaches require policies to learn cross-modal correspondences implicitly from limited demonstrations, without leveraging geometric priors. As a result, they are often data-inefficient and generalize poorly when visual observations are degraded. To address this limitation, we propose a framework that explicitly grounds physical contacts in the image domain. Using robot forward kinematics and camera calibration, we project tactile sensor locations directly onto the RGB image plane. We then render force-modulated Gaussian saliency maps to model spatial uncertainty arising from kinematic and calibration errors. By integrating these 2D spatial anchors through a zero-initialized conditioning architecture, our method injects physical contact priors into standard visual backbones while preserving pre-trained visual representations. We evaluate our method on six dexterous manipulation tasks in both simulation and the real world under severe visual occlusions. Real-world experiments show that explicit RGB-S grounding in the image domain improves real-world occluded manipulation success rates by $26.7$ percentage points over the strongest implicit visuo-tactile baseline, suggesting its improved spatial reasoning and robustness to occlusion. Project page: touch-as-saliency.github.io

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-16

Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare

Authors:
Maheed H. Ahmed↗Mahsa Ghasemi↗

arXiv:2605.01961v2 Announce Type: replace Abstract: Learning from human preference data is becoming a useful tool, from fine-tuning large language models to training reinforcement learning agents. However, in most scenarios, the model is trained on the average preference of all human evaluators, which, under large variations of preferences, can be unfair to minority groups. In this work, we consider fairness in dueling bandits, a standard framework for online learning from preference data. We assume that each user has a (potentially distinct) Condorcet winner, which is an arm preferred to every other arm. Using these user-specific Condorcet winners as reference points, we evaluate and score arms according to their performance relative to the corresponding winner. To promote fairness across heterogeneous users, we adopt the well-established Nash Social Welfare objective, which maximizes the product of user utilities, thereby inherently penalizing inequality and preventing the marginalization of any single user. Within this framework, we construct a hard instance to establish a regret lower bound of $\Omega(T^{2/3}\min(K,D)^\frac{1}{3})$ for a time horizon $T$, $K$ arms, and $D$ users, which, to the best of our knowledge, is the first result quantifying the cost of fairness in dueling bandits with heterogeneous preferences. We then present the Fair-Explore-Then-Commit and Fair-$\epsilon$-Greedy algorithms with a Condorcet winner identification phase. We further derive their regret upper bounds that match the lower-bound dependence on $T$ up to logarithmic factors.

Read & Discuss → View Source →
15.
arXiv (quant-ph) 2026-06-17

Active Quantum Reservoir Engineering: Using a Qubit to Manipulate its Environment

Authors:
Marcelo Janovitch↗Matteo Brunelli↗Patrick P. Potts↗

arXiv:2505.16898v4 Announce Type: replace Abstract: Quantum reservoir engineering leverages dissipative processes to achieve desired behavior, with applications ranging from entanglement generation to quantum error correction. Therein, a structured environment acts as an entropy sink for the system and no time-dependent control over the system is required. We develop a theoretical framework for active reservoir engineering, where time-dependent control over a quantum system is used to manipulate its environment. In this case, the system may act as an entropy sink for the environment. Our framwork captures the dynamical interplay between system and environment, and provides an intuitive picture of how finite-size effects and system-environment correlations allow for manipulating the environment by repeated initialization of the quantum system. We illustrate our results with two examples: a superconducting qubit coupled to an environment of two-level systems and a semiconducting quantum dot coupled to nuclear spins. In both scenarios, we find qualitative agreement with previous experimental results, illustrating how active control can unlock new functionalities in open quantum systems.

Read & Discuss → View Source →
16.
arXiv (CS.CV) 2026-06-12

Heterogeneous LiDAR Early Fusion and Learned Re-Ranking Strategy for Robust Long-Term Place Recognition in Unstructured Environments

Authors:
Judith Vilella-Cantos↗Juan Jos\'e Cabrera↗M\'onica Ballesta↗David Valiente↗Luis Pay\'a↗

Robust localization in unstructured environments, such as agricultural fields, is a critical challenge for autonomous systems. LiDAR sensors provide detailed 3D information about the environment and are invariant to lighting conditions. For this reason, LiDAR-based place recognition methods have gained significant attention. In this paper, we propose MinkUNeXt-VINE++, a novel approach that combines early fusion of heterogeneous LiDAR data from two sensors (Livox Mid-360 and Velodyne VLP-16) and a learned re-ranking strategy in inference time. This fusion leverages the strengths of each sensor to provide a more comprehensive representation of the environment. Additionally, the re-ranking approach is particularly important in repetitive environments, such as vineyards, as finding true positives is a major challenge. We evaluated our approach using the TEMPO-VINE dataset, which provides heterogeneous LiDAR data in vineyard environments across different phenological stages. Our results demonstrate that MinkUNeXt-VINE++ significantly improves place recognition performance compared to single-sensor approaches and state-of-the-art methods. MinkUNeXt-VINE++ achieves a 20% improvement in the Recall@1 metric compared to single-sensor approaches, and +30% including re-ranking. The code of our method is publicly available for reproduction.

Read & Discuss → View Source →
17.
arXiv (quant-ph) 2026-06-11

Dynamically Optimal Unraveling Schemes for Simulating Lindblad Equations

Authors:
Yu Cao↗Mingfeng He↗Xiantao Li↗

arXiv:2509.19887v2 Announce Type: replace Abstract: Stochastic unraveling schemes are powerful computational tools for simulating Lindblad equations, offering significant reductions in memory requirements. However, this advantage is accompanied by increased stochastic uncertainty, and the question of optimal unraveling remains open. In this work, we investigate unraveling schemes driven by Brownian motion or Poisson processes and present a comprehensive parametric characterization of these approaches. For the case of a single Lindblad operator and one noise term, this parametric family provides a complete description for unraveling scheme with pathwise norm-preservation. We further analytically derive dynamically optimal quantum state diffusion (DO-QSD) and dynamically optimal quantum jump process (DO-QJP) that minimize the growth rate of the variance of an observable locally in time. Compared to jump process ansatz, DO-QSD offers two notable advantages: firstly, the variance for DO-QSD can be rigorously shown not to exceed that of any jump-process ansatz locally in time; secondly, it has very simple expressions. Numerical results demonstrate that the proposed DO-QSD scheme may achieve substantial reductions in the variance of observables and the resulting simulation error.

Read & Discuss → View Source →
18.
arXiv (CS.AI) 2026-06-12

Prefill Awareness in Large Language Models

Authors:
Andy Wang↗Parv Mahajan↗David Demitri Africa↗Alexandra Souly↗Jordan Taylor↗Robert Kirk↗

arXiv:2606.12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs. If AI models can recognize and act on the fact their prior assistant messages have been inserted or edited, the effectiveness and validity of these methods could be compromised. We investigate whether frontier language models can distinguish between tampered and untampered assistant-side context, a capability we call prefill awareness. To do so, we construct a binary preference benchmark across three prefill mechanisms, filtering for cases where models show consistent stances. We find that frontier models show substantial prefill awareness: Claude Opus 4.5 detects prefills opposing its preferences in 9-35% of cases with a 0% false positive rate when prompted; additionally, models often revert towards baseline behavior without explicitly reporting that the prefill was foreign. Controlled ablations later also show that detection and resistance rely on different cues, where stylistic mismatch mainly affects whether models flag a prefill as foreign, while preference mismatch mainly affects whether they revert toward their baseline answer. We also examine more realistic agentic settings such as misalignment-continuation evaluations and SWE-bench trajectories, where frontier models sometimes disavow prefilled assistant turns in ways that depend strongly on dataset, task success, and hidden formatting artifacts. Our results indicate that prefill awareness is already a substantial confound for some prefill-based methods. We recommend that model developers track this capability in frontier systems.

Read & Discuss → View Source →
19.
arXiv (CS.CV) 2026-06-17

WeaveLA: Event Driven Cross-Subtask Latent Memory Weaving for Repetitive Robot Manipulation

Authors:
Shoujing Zhu↗Zhenyang Liu↗Fungmiu Wang↗Jiafeng Wang↗Bo Yue↗Guiliang Liu↗Simo Wu↗Xiangyang Xue↗Taiping Zeng↗

Vision-Language-Action (VLA) policies have achieved remarkable single-step manipulation, yet they remain brittle precisely where each stage depends on what was just completed. The core issue is structural: short-window VLAs lack an explicit channel for rouxting information across sub-task boundaries, and existing memory-augmented variants either write at every frame, retrieve from demonstration-time stages, or fire at sub-goal events without performing an explicit sub-task-to-sub-task hand-off into the action expert. We identify the sub-goal completion event as the natural temporal unit for cross-subtask memory hand-off, and present WeaveLA (Weave Latent memory for Vision-Language-Action policies), a cross-subtask memory interface that, on top of a frozen VLA backbone, compresses each completed segment into latent tokens via query-driven attention pooling and routes them directly into the action-generation path of the next sub-task. This event-triggered, action-side design preserves the base policy's short-window interface while adding a lightweight cross-subtask channel. Through stratified evaluation on RoboMME with a $\pi_{0.5}$ backbone, WeaveLA's gains land exactly where the channel is needed: on the hardest repetition slice (SwingXtimes, $N{=}3$), success rises from $0\%$ to $47.8\%$, while single-execution episodes remain unchanged. Per-episode paired analysis confirms the gains are confined to tasks whose causal structure requires cross-subtask information.

Read & Discuss → View Source →
20.
arXiv (CS.CV) 2026-06-17

Not Truly Multilingual: Script Consistency as a Missing Dimension in VLM Evaluation

Authors:
Prabhjot Singh↗Bhushan Pawar↗Madhu Reddiboina↗Rajvee Sheth↗

Current multilingual evaluations for Vision-Language Models (VLMs) assume a one-to-one mapping between language and orthography, overlooking billions of users of multi-script languages. We introduce PuMVR (Punjabi Multimodal Visual Reasoning), a benchmark of 1,000 strictly parallel image-text instances across Punjabi's three active scripts: Gurmukhi, Shahmukhi, and Roman. Evaluating 10 state-of-the-art VLMs, we expose a substantial and systematic Script Gap. Models frequently solve visual tasks in one script while failing identical tasks in another, with accuracy deltas reaching 16%. Crucially, visual input boosts absolute performance uniformly yet does not close the orthographic gap. Furthermore, cross-script in-context transfer is highly brittle, exposing script-locked knowledge representation. Supported by McNemar tests across all script pairs, our findings demonstrate that current "multilingual" VLMs are not truly multi-script. We propose the Script Consistency Rate (SCR), which falls as low as 24.8% on our benchmark, as a mandatory metric for script-agnostic evaluation to ensure equitable AI access. Data and code are available at: https://github.com/prabhjotschugh/Not-Truly-Multilingual-PuMVR.

Read & Discuss → View Source →
21.
arXiv (CS.CL) 2026-06-11

Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

Authors:
Kexin Ding↗Yang Zhou↗Can Jin↗Feng Tong↗Mu Zhou↗Dimitris N. Metaxas↗

The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety in real-world applications. Consequently, the field is undergoing an emerging paradigm shift from isolated skill creation to automated, evaluation-driven skill evolution. In this survey, we systematically examine the landscape of skill evolution and evaluation beyond foundational skill creation. We categorize evolution into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, showing how each element contributes to improving skill utility and reliability. We also provide an analysis of six skill-centric benchmark categories, identifying structural gaps in benchmark coverage, trade-offs, and metric richness to advance skill research. Finally, we identify open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe. The project URL is https://github.com/Cassie07/AgentSkill_Survey

Read & Discuss → View Source →
22.
arXiv (CS.CL) 2026-06-17

Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs

Authors:
Tingchao Fu↗Wenkai Wang↗Fanxiao Li↗Huadong Zhang↗Jinhong Zhang↗Dayang Li↗Yunyun Dong↗Renyang Liu↗Wei Zhou↗

Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text–image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones. Our in-depth empirical analysis reveals that the entity knowledge in MLLMs is not stored as a unified representation, but is instead distributed across disentangled modality-specific pathways. As a result, updates biased toward multimodal queries fail to propagate effectively to unimodal circuits. To bridge this gap, we propose DECODE, which explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge. Extensive experiments demonstrate that DECODE consistently achieves effective knowledge updates under different modality triggers, thereby mitigating editing decoupling failures.

Read & Discuss → View Source →
23.
arXiv (CS.AI) 2026-06-11

When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control

Authors:
Guilin Zhang↗Chuanyi Sun↗Kai Zhao↗Shahryar Sarkani↗John Fossaceca↗

arXiv:2605.26418v2 Announce Type: replace-cross Abstract: A properly calibrated rule-based autoscaler can beat every one of six mainstream deep reinforcement learning (DRL) algorithms on cost across every workload we test - so when, if ever, does DRL actually help? We study this in RLScale-Bench, a reproducible benchmark and evaluation protocol for DRL on adaptive resource control, where an agent allocates compute to a dynamic workload under cost and service-level constraints. We evaluate PPO, DQN, A2C, SAC, TD3, and DDPG under matched architectures, training budgets, and reward functions against a calibrated rule-based baseline across six workload patterns and five seeds (240 runs), instantiate the benchmark on Kubernetes Horizontal Pod Autoscaling, and probe distribution-shift generalization. Three findings challenge common assumptions: (i) the calibrated controller achieves the lowest cost on all six workloads, though it trails the best RL agents on bursty and flash traffic; (ii) discrete-action algorithms outperform continuous-action ones by one to two orders of magnitude in constraint violations due to action-space mismatch; and (iii) no single algorithm dominates across workloads, with rankings shifting by up to four positions. The bottleneck in RL-based resource control is not algorithm selection but baseline calibration, reward engineering, and realistic evaluation protocols.

Read & Discuss → View Source →
24.
arXiv (CS.CL) 2026-06-19

LaViSA: A Language and Vision Structural Ambiguity Benchmark

Authors:
Lee Sangmyeong↗Shun Inadumi↗Koichiro Yoshino↗

Structural ambiguity arises when a single sentence admits multiple valid interpretations due to its syntactic structure, posing a fundamental challenge for language understanding. Visual scenes serve as useful cues for resolving such ambiguity, and Vision and Language Models (VLMs) need to be capable of deriving possible semantic interpretations from visual scenes. We introduce Language and Vision Structural Ambiguity (LaViSA), a benchmark designed to evaluate the ability of VLMs to resolve structural ambiguity leveraging visual scenes. LaViSA consists of ambiguous sentences, their disambiguated sentences, and corresponding images of these disambiguated sentences across seven ambiguity categories. Using LaViSA, we conduct a comprehensive evaluation of diverse VLMs, including both proprietary and open-source models with varying parameter scales and reasoning capabilities. Experimental results show that although recent VLMs can leverage visual scenes to resolve structural ambiguity to a some extent, they still struggle with certain ambiguity types and visually subtle semantic distinctions, indicating remaining limitations in resolving structural ambiguity using visual scenes.

Read & Discuss → View Source →
25.
arXiv (CS.CV) 2026-06-18

Prior-guided Fusion of Multimodal Features for Change Detection from Optical-SAR Images

Authors:
Xuanguang Liu↗Lei Ding↗Yujie Li↗Chenguang Dai↗Zhenchao Zhang↗Mengmeng Li↗Ziyi Yang↗Yifan Sun↗Yongqi Sun↗Hanyun Wang↗Lorenzo Bruzzone↗

Multimodal change detection (MMCD) identifies changed areas in multimodal remote sensing data, demonstrating significant application value in land use monitoring and urban sustainable development. However, literature MMCD approaches exhibit limitations in both cross-modal interaction and exploiting modality-specific characteristics. This leads to insufficient modeling of fine-grained change information, thus hindering the precise detection of semantic changes. To address these problems, we propose STSF-Net, a framework designed for MMCD between optical and SAR images. STSF-Net jointly models modality-specific and spatio-temporal common features to enhance change representations. Specifically, modality-specific features are exploited to capture genuine semantic change signals, while spatio-temporal common features are embedded to suppress pseudo-changes caused by differences in imaging mechanisms. Furthermore, we introduce an optical and SAR feature fusion strategy that adaptively adjusts multimodal feature importance based on semantic priors obtained from visual foundation models. Finally, we introduce the novel Delta-SN6 dataset, the first openly-accessible multiclass MMCD benchmark consisting of very-high-resolution fully polarimetric SAR and optical images. Experimental results on Delta-SN6, BRIGHT, and Wuhan datasets demonstrate that our method outperforms the state-of-the-art by 3.21%, 0.87%, and 1.32% in mIoU, respectively.

Read & Discuss → View Source →