Multimodal Retrieval-Augmented Generation (MRAG) addresses key limitations of Multimodal Large Language Models (MLLMs), such as hallucination and outdated knowledge. However, current MRAG systems struggle to distinguish whether retrieved multimodal data truly supports the semantic core of an answer or merely provides superficial relevance. Existing metrics often rely on heuristic position-based confidence, which fails to capture the informational density of multimodal entities. To address this, we propose Multi-modal Evidence Grounding (MEG), a semantic-aware metric that quantifies the contribution of retrieved evidence. Unlike standard confidence measures, MEG utilizes Semantic Certainty Anchoring, focusing on high-IDF information-bearing tokens that better capture the semantic core of the answer. Building on MEG, we introduce MEG-RAG, a framework that trains a multimodal reranker to align retrieved evidence with the semantic anchors of the ground truth. By prioritizing high-value content based on semantic grounding rather than token probability distributions, MEG-RAG improves the accuracy and multimodal consistency of generated outputs. Extensive experiments on the M$^2$RAG benchmark show that MEG-RAG consistently outperforms strong baselines and demonstrates robust generalization across different teacher models.

LLM agents increasingly rely on reusable skills, capability packages that combine instructions, control flow, constraints, and tool calls. In most current agent systems, however, skills are still represented by text-heavy artifacts, including SKILL{.}md-style documents and structured records whose machine-usable evidence remains embedded largely in natural-language descriptions. This poses a challenge for skill-centered agent systems: managing skill collections and using skills to support agent both require reasoning over invocation interfaces, execution structure, and concrete side effects that are often entangled in a single textual surface. An explicit representation of skill knowledge may therefore help make these artifacts easier for machines to acquire and leverage. Drawing on Memory Organization Packets, Script Theory, and Conceptual Dependency from Schank and Abelson's classical work on linguistic knowledge representation, we introduce what is, to our knowledge, the first structured representation for agent skill artifacts that disentangles skill-level scheduling signals, scene-level execution structure, and logic-level action and resource-use evidence: the Scheduling-Structural-Logical (SSL) representation. We instantiate SSL with an LLM-based normalizer and evaluate it on a corpus of skills in two tasks, Skill Discovery and Risk Assessment, and superiorly outperform the text-only baselines: in Skill Discovery, SSL improves MRR from 0.573 to 0.707; in Risk Assessment, it improves macro F1 from 0.744 to 0.787. These findings reveal that explicit, source-grounded structure makes agent skills easier to search and review. They also suggest that SSL is best understood as a practical step toward more inspectable, reusable, and operationally actionable skill representations for agent systems, rather than as a finished standard or an end-to-end mechanism for managing and using skills.

Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-attention architectures offer no explicit channel telling the network where to apply the edit. We introduce AdaptEdit, a co-trained, instruction- and region-aware adapter framework that retro-fits a frozen DiT into a precise local editor without modifying its backbone weights. A lightweight Block Adapter at every transformer block injects a structured condition stream that factorizes what to edit (instruction semantics) from where to edit (spatial mask); a learned SpatialGate routes the adapter signal selectively into the edit region while keeping the rest of the image near-identical to the source; and a Region-Aware Loss focuses the training objective on the changing pixels. Because these components make the backbone's internal representation mask-aware end-to-end, a thin MaskPredictor head trained jointly with the editor can ground the edit region directly from the instruction and source image -- eliminating any user-mask requirement at deployment. We evaluate on two complementary benchmarks: MagicBrush (paired ground-truth targets) to measure pixel-level preservation and edit accuracy, and Emu-Edit Test (no ground-truth images, 9 diverse edit categories) to stress-test instruction following and generalization across edit types. On both, AdaptEdit achieves state-of-the-art results, simultaneously outperforming mask-free and oracle-mask baselines. A seven-variant ablation cleanly isolates the contribution of each component.

For the use case of comparing the performance of clustering algorithms whose output is a contingency table, a single performance metric for contingency tables is needed. Such a metric is vital for comparative performance analysis of clustering algorithms. A survey of publicly available literature did not show the presence of such a metric. Metrics do exist for vector pairs of truth values and predicted values, which are an alternative form of output of clustering algorithms. However, the metrics for vector pairs do not reveal the presence of detailed features that are apparent in contingency tables. This paper presents the Associativity Peakiness (AP) metric, which characterizes aspects of clustering algorithm performance that are critical for predicting a clustering algorithm's performance when deployed. The AP metric is analogous to measures of quality for confusion matrices that are outputs of supervised learning algorithms. This paper presents results from simulations in which 500 contingency tables were generated for multiple test scenarios. The results show that for the use case of evaluating clustering algorithms, the AP metric characterizes performance of contingency tables with higher dynamic range than publicly available metrics, and that it is computationally more efficient than comparable publicly available metrics.

We study the $K$-armed logistic bandit problem, where at each round, the agent observes $K$ feature vectors associated with $K$ actions. Existing approaches that achieve a rate-optimal $\tilde{\mathcal{O}}(\sqrt{dT})$ regret bound rely heavily on context diversity assumptions, such as strict positivity of the minimum eigenvalue of a context covariance matrix. These assumptions, however, impose strong restrictions on the context process, as they rule out the situation where the context vectors are concentrated in a low-dimensional subspace. In this paper, we propose SupSplitLog, which, to the best of our knowledge, is the first algorithm for logistic bandits that achieves $\tilde{\mathcal{O}}(\sqrt{dT})$ regret without any context diversity assumption. The key idea is to split the collected samples into two disjoint subsets when constructing estimators; one is used to compute an initial-point estimator, while the other is used to apply a Newton-type one-step correction procedure. The splitting rule is carefully designed to balance the accuracy requirements of the initial-point estimator and the one-step correction procedure. Moreover, SupSplitLog strictly improves on the existing algorithms in terms of the dependence on dimension $d$ in the regret upper bound. Furthermore, SupSplitLog can be adapted simply to deduce a regret bound that grows with a data-dependent complexity measure, avoiding a direct dependence on $d$, which is favorable when the context vectors are concentrated in a low-dimensional subspace. We also provide experimental results that demonstrate numerically the superiority of our algorithm, validating the theoretical results.

Pumping fluids is fundamental to a wide range of industrial, environmental, and biomedical applications. Among various pumping mechanisms, peristaltic pumps enable efficient and safe fluid transport by deforming an elastic tube without direct contact with the working fluid. Although previous studies have introduced mechanical, pneumatic, or magnetic actuations to drive membrane deformation, these approaches often lead to complex pump architectures and control schemes. In this study, we present a soft membrane pump that achieves peristaltic motion through a single pneumatic input combined with an embedded passive magnet. The actuation mechanism and system dynamics were analyzed and simplified through modeling. Numerical simulations were conducted to predict the internal fluid flow, and the magneto-elastic hysteresis behavior observed in the simulations was successfully validated by experiments with a proof-of-concept prototype.

Large language models (LLMs) have recently demonstrated strong reasoning capabilities and attracted increasing research attention in the field of autonomous driving (AD). However, safe application of LLMs on AD perception and prediction still requires a thorough understanding of both the dynamic traffic agents and the static road infrastructure. To this end, this study introduces a framework to evaluate the capability of LLMs in understanding the behaviors of dynamic traffic agents and the topology of road networks. The framework leverages frozen LLMs as the reasoning engine, employing a traffic encoder to extract spatial-level scene features from observed trajectories of agents, while a lightweight Convolutional Neural Network (CNN) encodes the local high-definition (HD) maps. To assess the intrinsic reasoning ability of LLMs, the extracted scene features are then transformed into LLM-compatible tokens via a reprogramming adapter. By residing the prediction burden with the LLMs, a simpler linear decoder is applied to output future trajectories. The framework enables a quantitative analysis of the influence of multi-modal information, especially the impact of map semantics on trajectory prediction accuracy, and allows seamless integration of frozen LLMs with minimal adaptation, thereby demonstrating strong generalizability across diverse LLM architectures and providing a unified platform for model evaluation.

Rotating FMCW radar odometry methods often assume flat ground conditions. While this assumption is sufficient in many scenarios, including urban environments or flat mining setups, the highly dynamic terrain of subarctic environments poses a challenge to standard feature extraction and state estimation techniques. This paper benchmarks three existing radar odometry methods under demanding conditions, exhibiting up to 13° in pitch and 4° in roll difference between consecutive scans, with absolute pitch and roll reaching 30° and 8°, respectively. Furthermore, we propose a novel radar-inertial odometry method utilizing tilt-proximity submap search and a hard threshold for vertical displacement between scan points and the estimated axis of rotation. Experimental results demonstrate a state-of-the-art performance of our method on an urban baseline and a 0.3% improvement over the second-best comparative method on a 2-kilometer-long dynamic trajectory. Finally, we analyze the performance of the four evaluated methods on a complex radar sequence characterized by high lateral slip and a steep ditch traversal.

Systematic ablations are essential to attribute performance gains in AI Virtual Cells, yet they are rarely performed because biological repositories are under-standardized and tightly coupled to domain-specific data and formats. While recent coding agents can translate ideas into implementations, they typically stop at producing code and lack a verifier that can reproduce strong baselines and rigorously test which components truly matter. We introduce AblateCell, a reproduce-then-ablate agent for virtual cell repositories that closes this verification gap. AblateCell first reproduces reported baselines end-to-end by auto-configuring environments, resolving dependency and data issues, and rerunning official evaluations while emitting verifiable artifacts. It then conducts closed-loop ablation by generating a graph of isolated repository mutations and adaptively selecting experiments under a reward that trades off performance impact and execution cost. Evaluated on three single-cell perturbation prediction repositories (CPA, GEARS, BioLORD), AblateCell achieves 88.9% (+29.9% to human expert) end-to-end workflow success and 93.3% (+53.3% to heuristic) accuracy in recovering ground-truth critical components. These results enable scalable, repository-grounded verification and attribution directly on biological codebases.

Language-driven 3D Gaussian Splatting (3DGS) editing provides a more convenient approach for modifying complex scenes in VR/AR. Standard pipelines typically adopt a two-stage strategy: first editing multiple 2D views, and then optimizing the 3D representation to match these edited observations. Existing methods mainly improve view consistency through multi-view feature fusion, attention filtering, or iterative recalibration. However, they fail to explicitly address a more fundamental issue: the semantic correspondence between edited 2D evidence and 3D Gaussians. To tackle this problem, we propose TransSplat, which formulates language-driven 3DGS editing as a multi-view unbalanced semantic transport problem. Specifically, our method establishes correspondences between visible Gaussians and view-specific editing prototypes, thereby explicitly characterizing the semantic relationship between edited 2D evidence and 3D Gaussians. It further recovers a cross-view shared canonical 3D edit field to guide unified 3D appearance updates. In addition, we use transport residuals to suppress erroneous edits in non-target regions, mitigating edit leakage and improving local control precision. Qualitative and quantitative results show that, compared with existing 3D editing methods centered on enhancing view consistency, TransSplat achieves superior performance in local editing accuracy and structural consistency.

Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like conversational systems. Traditional cascaded speech processing pipelines suffer from critical limitations, including accumulated latency, information loss, and error propagation across modules. To address these issues, recent efforts focus on the end-to-end audio large language models (LLMs) like GPT-4o, which primarily unify speech understanding and generation task. However, most of these models are inherently half-duplex, and rely on a suite of separate, task-specific front-end components, such as voice activity detection (VAD) and turn-taking detection (TD). In our development of speech assistant, we observed that optimizing the speech front-end is equally crucial as advancing the back-end unified model for achieving seamless, responsive interactions. To bridge this gap, we propose the first unified audio front-end LLM (UAF) tailored for full-duplex speech systems. Our model reformulates diverse audio front-end tasks into a single auto-regressive sequence prediction problem, including VAD, TD, speaker recognition (SR), automatic speech recognition (ASR) and question answer (QA). It takes streaming fixed-duration audio chunk (e.g., 600 ms) as input, leverages a reference audio prompt to anchor the target speaker at the beginning, and regressively generates discrete tokens encoding both semantic content and system-level state controls (e.g., interruption signals). Experiments demonstrate that our model achieves leading performance across multiple audio front-end tasks and significantly enhances response latency and interruption accuracy in real-world interaction scenarios.

In self-supervised learning, self-distilled methods have shown impressive performance, learning representations useful for downstream tasks and even displaying emergent properties. However, state-of-the-art methods usually rely on ensembles of complex mechanisms, with many design choices that are empirically motivated and not well understood. In this work, we explore the role of self-distillation within learning dynamics. Specifically, we isolate the effect of self-distillation by training a group of randomly initialized networks, removing all other common components such as projectors, predictors, and even pretext tasks. Our findings show that even this minimal setup can lead to learned representations with non-trivial improvements over a random baseline on downstream tasks. We also demonstrate how this effect varies with different hyperparameters and present a short analysis of what is being learned by the models under this setup.

We introduce RosettaSearch, an inference-time multi-objective optimization approach for backbone conditioned protein sequence design. We use large language models (LLMs) as a generative optimizer within a search algorithm capable of controlled exploration and exploitation, using rewards computed from RosettaFold3, a structure prediction model, under a strict computational budget. In a large-scale evaluation, we apply RosettaSearch to 400 suboptimal sequences generated by LigandMPNN (a state-of-the-art model trained for protein sequence design), recovering high-fidelity designs that LigandMPNN's single-pass decoding fails to produce. RosettaSearch's designs show improvements in structural fidelity metrics ranging between 18% to 68%, translating to a 2.5x improvement in design success rate. We observe that these gains in success rate are robust when RosettaSearch-designed sequences are evaluated with an independent structure prediction oracle (Chai-1) and generalize across two distinct LLM families (o4-mini and Gemini-3), with performance scaling consistently with reasoning capability. We further demonstrate that RosettaSearch improves the sequence fidelity of ProteinMPNN designs for de novo backbones from the Dayhoff atlas, showing that the approach generalizes beyond native protein structures to computationally generated backbones. We also demonstrate a multi-modal extension of RosettaSearch with vision-language models, where images of predicted protein structures are used as feedback to incorporate structural context to guide protein sequence generation. To our knowledge, this is the first large-scale demonstration that LLMs can serve as effective generative optimizers for backbone-conditioned protein sequence design, yielding systematic gains without any model retraining.

Subjective NLP datasets typically aggregate annotator judgments into a single gold label, making it difficult to diagnose whether disagreement reflects unclear criteria, collapsed distinctions, or legitimate plurality. We propose a \emph{schema-level diagnostic} for auditing expert-designed annotation schemas \emph{prior to} gold-label commitment, using only multi-annotator criterion judgments. The diagnostic separates two failure modes: unstable criteria with hard-to-operationalize boundaries, and systematic overlap that blurs the boundaries between mutually exclusive categories. Applied to persuasive value extraction in commercial documents, we find that disagreement is not diffuse: instability concentrates in a few criteria, while nearly half of covered sentences activate multiple categories. These signals align with where domain experts disagree, yielding an evidence-based audit for tightening guidelines, revising category structure, or reconsidering the annotation paradigm.

Existing video coding for machines is often trained for a specific downstream task and model. As a result, the compressed representation becomes tightly coupled to the end task, making it difficult to scale across multiple tasks or adapt to model updates. We propose PAT-VCM, a plug-and-play auxiliary-token framework for video coding for machines. PAT-VCM keeps a shared baseline compressed stream and augments it with lightweight task-aware auxiliary tokens, allowing different downstream tasks to recover the information they need without retraining a separate codec for each task. The framework supports three forms of auxiliary information: visual residual tokens, prompt/control tokens, and semantic tokens. We evaluate PAT-VCM on segmentation, depth estimation, and semantic recognition. A shared detection-oriented auxiliary branch provides a reusable first refinement, task-specific visual branches improve segmentation and depth, prompt tokens provide further segmentation gains at negligible bitrate, and semantic tokens achieve strong recognition performance with extremely low overhead. These results suggest that a shared compressed representation, combined with lightweight task-aware auxiliary tokens, is a practical and scalable alternative to tightly task-coupled VCM design.

End-to-end diffusion planning has shown strong potential for autonomous driving, but the physical feasibility of generated trajectories remains insufficiently addressed. In particular, generated trajectories may exhibit local geometric irregularities, violate trajectory-level kinematic constraints, or deviate from the drivable area, indicating that the commonly used noise-centric formulation in diffusion planning is not yet well aligned with the trajectory space where feasibility is more naturally characterized. To address this issue, we propose FeaXDrive, a feasibility-aware trajectory-centric diffusion planning method for end-to-end autonomous driving. The core idea is to treat the clean trajectory as the unified object for feasibility-aware modeling throughout the diffusion process. Built on this trajectory-centric formulation, FeaXDrive integrates adaptive curvature-constrained training to improve intrinsic geometric and kinematic feasibility, drivable-area guidance within reverse diffusion sampling to enhance consistency with the drivable area, and feasibility-aware GRPO post-training to further improve planning performance while balancing trajectory-space feasibility. Experiments on the NAVSIM benchmark show that FeaXDrive achieves strong closed-loop planning performance while substantially improving trajectory-space feasibility. These findings highlight the importance of explicitly modeling trajectory-space feasibility in end-to-end diffusion planning and provide a step toward more reliable and physically grounded autonomous driving planners.

Frontier coding agents solve complex tasks when given complete context but collapse when specifications are incomplete or ambiguous. The bottleneck is not raw capability, but judgment: knowing when to act autonomously and when to ask for help. Current benchmarks are blind to this failure mode. They supply unambiguous detailed instructions and solely reward execution correctness, so an agent that makes a lucky guess for a missing requirement will score identically to one that would have asked to be certain. We present HiL-Bench (Human-in-the-Loop Benchmark) to measure this selective escalation skill. Each task contains human-validated blockers (missing information, ambiguous requests, contradictory information) that surface only through progressive exploration, not upfront inspection. Our core metric, Ask-F1, the harmonic mean of question precision and blocker recall, captures the tension between over-asking and silent guessing; its structure architecturally prevents gaming through question spam. Evaluation across SWE and text-to-SQL domains reveals a large universal judgment gap: no frontier model recovers more than a fraction of its full-information performance when deciding whether to ask. Failure analysis identifies three key help-seeking patterns: overconfident wrong beliefs with no gap detection; high uncertainty detection yet persistent errors; broad, imprecise escalation without self-correction. These consistent patterns confirm poor help-seeking is a model-level flaw, not task-specific. RL training on shaped Ask-F1 reward shows judgment is trainable: a 32B model improves both help-seeking quality and task pass rate, with gains that transfer across domains. The model does not learn domain-specific heuristics for when to ask; it learns to detect unresolvable uncertainty and act on it.

Autonomous agents operating in dynamic and safety-critical environments require decision-making frameworks that are both computationally efficient and physically grounded. However, many existing approaches rely on end-to-end learning, which often lacks interpretability and explicit mechanisms for ensuring consistency with physical constraints. In this work, we propose an event-centric world modeling framework with memory-augmented retrieval for embodied decision-making. The framework represents the environment as a structured set of semantic events, which are encoded into a permutation-invariant latent representation. Decision-making is performed via retrieval over a knowledge bank of prior experiences, where each entry associates an event representation with a corresponding maneuver. The final action is computed as a weighted combination of retrieved solutions, providing a transparent link between decision and stored experiences. The proposed design enables structured abstraction of dynamic environments and supports interpretable decision-making through case-based reasoning. In addition, incorporating physics-informed knowledge into the retrieval process encourages the selection of maneuvers that are consistent with observed system dynamics. Experimental evaluation in UAV flight scenarios demonstrates that the framework operates within real-time control constraints while maintaining interpretable and consistent behavior.

Remote sensing semantic segmentation requires models that can jointly capture fine spatial details and high-level semantic context across complex scenes. While classical encoder-decoder architectures such as U-Net remain strong baselines, they often struggle to fully exploit global semantics and structured feature interactions. In this work, we propose HQF-Net, a hybrid quantum-classical multi-scale fusion network for remote sensing image segmentation. HQF-Net integrates multi-scale semantic guidance from a frozen DINOv3 ViT-L/16 backbone with a customized U-Net architecture through a Deformable Multiscale Cross-Attention Fusion (DMCAF) module. To enhance feature refinement, the framework further introduces quantum-enhanced skip connections (QSkip) and a Quantum bottleneck with Mixture-of-Experts (QMoE), which combines complementary local, global, and directional quantum circuits within an adaptive routing mechanism. Experiments on three remote sensing benchmarks show consistent improvements with the proposed design. HQF-Net achieves 0.8568 mIoU and 96.87% overall accuracy on LandCover.ai, 71.82% mIoU on OpenEarthMap, and 55.28% mIoU with 99.37% overall accuracy on SeasoNet. An architectural ablation study further confirms the contribution of each major component. These results show that structured hybrid quantum-classical feature processing is a promising direction for improving remote sensing semantic segmentation under near-term quantum constraints.

At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Generative Video Codebook Codec (GVCC), a zero-shot framework in which a pretrained video generative model serves directly as the decoder, and the transmitted bitstream specifies its generation trajectory. Modern rectified-flow video models are typically sampled with deterministic ODE solvers, which leave no per-step stochastic channel for transmitting compressed information. GVCC addresses this by converting the deterministic flow sampler into an equivalent marginal-preserving stochastic process, so that information can be transmitted by encoding the per-step stochastic innovations. Unlike images, videos introduce longer temporal dependencies and more diverse conditioning modes. We instantiate GVCC in three practical modes: Text-to-Video (T2V) without a reference frame, autoregressive Image-to-Video (I2V) with tail latent correction, and First-Last-Frame-to-Video (FLF2V) with boundary-sharing Group of Pictures (GOP) chaining. On UVG, GVCC achieves the lowest LPIPS among evaluated baselines across three representative bitrate regimes (down to ${\sim}$0.003\,bpp), with 65\% LPIPS reduction over DCVC-RT at matched bitrate.

Humanoid robots require diverse motor skills to integrate into complex environments, but bridging the kinematic and dynamic embodiment gap from human data remains a major bottleneck. We demonstrate through Hessian analysis that traditional optimization-based retargeting is inherently non-convex and prone to local optima, leading to physical artifacts like joint jumps and self-penetration. To address this, we reformulate the targeting problem as learning data distribution rather than optimizing optimal solutions, where we propose NMR, a Neural Motion Retargeting framework that transforms static geometric mapping into a dynamics-aware learned process. We first propose Clustered-Expert Physics Refinement (CEPR), a hierarchical data pipeline that leverages VAE-based motion clustering to group heterogeneous movements into latent motifs. This strategy significantly reduces the computational overhead of massively parallel reinforcement learning experts, which project and repair noisy human demonstrations onto the robot's feasible motion manifold. The resulting high-fidelity data supervises a non-autoregressive CNN-Transformer architecture that reasons over global temporal context to suppress reconstruction noise and bypass geometric traps. Experiments on the Unitree G1 humanoid across diverse dynamic tasks (e.g., martial arts, dancing) show that NMR eliminates joint jumps and significantly reduces self-collisions compared to state-of-the-art baselines. Furthermore, NMR-generated references accelerate the convergence of downstream whole-body control policies, establishing a scalable path for bridging the human-robot embodiment gap.

Robot action planning in the real world is challenging as it requires not only understanding the current state of the environment but also predicting how it will evolve in response to actions. Vision-language-action (VLA), which repurpose large-scale vision-language models for robot action generation using action experts, have achieved notable success across a variety of robotic tasks. Nevertheless, their performance remains constrained by the scope of their training data, exhibiting limited generalization to unseen scenarios and vulnerability to diverse contextual perturbations. More recently, world models have been revisited as an alternative to VLAs. These models, referred to as world action models (WAMs), are built upon world models that are trained on large corpora of video data to predict future states. With minor adaptations, their latent representation can be decoded into robot actions. It has been suggested that their explicit dynamic prediction capacity, combined with spatiotemporal priors acquired from web-scale video pretraining, enables WAMs to generalize more effectively than VLAs. In this paper, we conduct a comparative study of prominent state-of-the-art VLA policies and recently released WAMs. We evaluate their performance on the LIBERO-Plus and RoboTwin 2.0-Plus benchmarks under various visual and language perturbations. Our results show that WAMs achieve strong robustness, with LingBot-VA reaching 74.2% success rate on RoboTwin 2.0-Plus and Cosmos-Policy achieving 82.2% on LIBERO-Plus. While VLAs such as $π_{0.5}$ can achieve comparable robustness on certain tasks, they typically require extensive training with diverse robotic datasets and varied learning objectives. Hybrid approaches that partially incorporate video-based dynamic learning exhibit intermediate robustness, highlighting the importance of how video priors are integrated.

Large language models (LLMs) used for multiple-choice and pairwise evaluation tasks often exhibit selection bias due to non-semantic factors like option positions and label symbols. Existing inference-time debiasing is costly and may harm reasoning, while pointwise training ignores that the same question should yield consistent answers across permutations. To address this issue, we propose Permutation-Aware Group Relative Policy Optimization (PA-GRPO), which mitigates selection bias by enforcing permutation-consistent semantic reasoning. PA-GRPO constructs a permutation group for each instance by generating multiple candidate permutations, and optimizes the model using two complementary mechanisms: (1) cross-permutation advantage, which computes advantages relative to the mean reward over all permutations of the same instance, and (2) consistency-aware reward, which encourages the model to produce consistent decisions across different permutations. Experimental results demonstrate that PA-GRPO outperforms strong baselines across seven benchmarks, substantially reducing selection bias while maintaining high overall performance. The code is available on github (https://github.com/ECNU-Text-Computing/PA-GRPO).

Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research workflows, yet inadequately model scientific reasoning, resulting in surface-level conceptual recombinations that lack technical depth and scientific grounding. To address this issue, we propose \textbf{MoRI} (\textbf{Mo}tivation-grounded \textbf{R}easoning for Scientific \textbf{I}deation), a framework that enables LLMs to explicitly learn the reasoning process from research motivations to methodologies. The base LLM is initialized via supervised fine-tuning to generate a research motivation from a given context, and is subsequently trained under a composite reinforcement learning reward that approximates scientific rigor: (1) entropy-aware information gain encourages the model to uncover and elaborate high-complexity technical details grounded in ground-truth methodologies, and (2) contrastive semantic gain constrains the reasoning trajectory to remain conceptually aligned with scientifically valid solutions. Empirical results show that MoRI consistently outperforms strong commercial LLMs and complex agentic baselines across multiple dimensions, including novelty, technical rigor, and feasibility. The code is available on \href{https://github.com/ECNU-Text-Computing/IdeaGeneration}{GitHub}.

Creatively translating complex gameplay ideas into executable artifacts (e.g., games as Unity projects and code) remains a central challenge in computational game creativity. Gameplay design patterns provide a structured representation for describing gameplay phenomena, enabling designers to decompose high-level ideas into entities, constraints, and rule-driven dynamics. Among them, goal patterns formalize common player-objective relationships. Goal Playable Concepts (GPCs) operationalize these abstractions as playable Unity engine implementations, supporting experiential exploration and compositional gameplay design. We frame scalable playable pattern realization as a problem of constrained executable creative synthesis: generated artifacts must satisfy Unity's syntactic and architectural requirements while preserving the semantic gameplay meanings encoded in goal patterns. This dual constraint limits scalability. Therefore, we investigate whether contemporary large language models (LLMs) can perform such synthesis under engine-level structural constraints and generate Unity code (as games) structured and conditioned by goal playable patterns. Using 26 goal pattern instantiations, we compare a direct generation baseline (natural language -> C# -> Unity) with pipelines conditioned on a human-authored Unity-specific intermediate representation (IR), across three IR configurations and two open-source models (DeepSeek-Coder-V2-Lite-Instruct and Qwen2.5-Coder-7B-Instruct). Compilation success is evaluated via automated Unity replay. We propose grounding and hygiene failure modes, identifying structural and project-level grounding as primary bottlenecks.

Synthetic data generation is an important capability for privacy-preserving data sharing, system benchmarking and test data provisioning. For mixed-type data, existing synthesizers largely target dense, fixed-schema tables, but many modern data systems store and exchange sparse, semi-structured JSON with nested objects, variable-length arrays and optional keys. Applying tabular synthesizers to such data requires flattening records into wide, sparse tables, turning nested structure and arrays into column-layout artifacts. We present ORiGAMi, an autoregressive transformer architecture for modeling and synthesizing semi-structured records without flattening. ORiGAMi serializes JSON records into key, value, and structural tokens, and encodes token positions by their path in the document tree. Grammar and schema constraints enforce syntactically valid JSON and dataset-consistent structure. We evaluate ORiGAMi against VAE, GAN, diffusion, and autoregressive baselines that operate on flattened representations across six datasets ranging from dense tabular benchmarks to large-scale semi-structured collections. Across fidelity, detection, and utility metrics, ORiGAMi achieves the best score in 17 of 18 benchmark comparisons, while maintaining high privacy scores above 96% across all settings. These results establish native record modeling as a strong alternative to tabular synthesis pipelines, preserving structure while achieving state-of-the-art benchmark performance.

Identifying the full landscape of small and medium-sized enterprises (SMEs) in specialized industry sectors is critical for supply-chain resilience, yet existing business databases suffer from substantial coverage gaps -- particularly for sub-tier suppliers and firms in emerging niche markets. We propose a \textbf{Web--Knowledge--Web (W$\to$K$\to$W)} pipeline that iteratively (1)~crawls domain-specific web sources to discover candidate supplier entities, (2)~extracts and consolidates structured knowledge into a heterogeneous knowledge graph using domain-adapted few-shot LLM prompting, and (3)~uses the knowledge graph's topology and coverage signals to guide subsequent crawling toward under-represented regions of the supplier space. To quantify discovery completeness, we introduce a \textbf{coverage estimation framework} inspired by ecological species-richness estimators (Chao1, ACE) adapted for web-entity populations. Experiments on the semiconductor equipment manufacturing sector (NAICS 333242) demonstrate that the W$\to$K$\to$W pipeline achieves the highest precision (0.165) and F1 (0.123) among all methods while using only 144 pages -- 32\% fewer than the 213-page baseline budget -- building a knowledge graph of 664 entities and 542 relations with 100\% relation type-consistency.

Recent advances in multilingual representation learning aim to bridge the performance gap between high- and low-resource languages, yet their ability to preserve affective meaning across languages remains underexplored, particularly for underrepresented languages like Bengali. This research addresses cross-lingual sentiment misalignment between Bengali and English by introducing a controlled benchmarking framework evaluating four multilingual transformer models on parallel Bengali-English sentence pairs, stratified by dialect, to assess their representational stability. We demonstrate that a compressed model architecture exhibits a 28.7% "Sentiment Inversion Rate," fundamentally misinterpreting positive semantics as negative (or vice versa). Consequently, we identify a cross-lingual sentiment skew that we call "Asymmetric Empathy," where models systematically dampen or artificially amplify the affective weight of Bengali text relative to its exact English counterpart. Finally, we expose a key vulnerability regarding dialectal representation: a "Modern Bias" in the regional model, which exhibits a 57% increase in alignment error when processing the formal Bengali register compared to modern colloquial text. As foundational encoders continue to serve as safety classifiers and reward models for LLM pipelines, cross-lingual reliability becomes a critical concern. We therefore advocate for the integration of "Affective Stability" metrics into future cross-lingual benchmarks to detect and penalize polarity inversions, particularly in low-resource settings.

This paper introduces ParlaCAP, a large-scale dataset for analyzing parliamentary agenda setting across Europe, and proposes a cost-effective method for building domain-specific policy topic classifiers. Applying the Comparative Agendas Project (CAP) schema to the multilingual ParlaMint corpus of over 8 million speeches from 28 parliaments of European countries and autonomous regions, we follow a teacher-student framework in which a high-performing large language model (LLM) annotates in-domain training data and a multilingual encoder model is fine-tuned on these annotations for scalable data annotation. We show that this approach produces a classifier tailored to the target domain. Agreement between the LLM and human annotators is comparable to inter-annotator agreement among humans, and the resulting model outperforms existing CAP classifiers trained on manually-annotated but out-of-domain data. In addition to the CAP annotations, the ParlaCAP dataset offers rich speaker and party metadata, as well as sentiment predictions coming from the ParlaSent multilingual transformer model, enabling comparative research on political attention and representation across countries. We illustrate the analytical potential of the dataset with three use cases, examining the distribution of parliamentary attention across policy topics, sentiment patterns in parliamentary speech, and gender differences in policy attention.

To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement Learning (RL) using static datasets. However, these methods suffer from severe distributional shifts, as offline trajectories fail to capture the stochastic state transitions and real-time feedback of unconstrained wide web environments. In this paper, we propose a robust Online Reinforcement Learning WebAgent, designed to optimize its policy through direct, iterative interactions with unconstrained wide websites. Our approach comprises three core innovations: 1) Hierarchical Multi-Task Fine-tuning: We curate a comprehensive mixture of datasets categorized by functional primitives -- Planning, Acting, and Grounding -- establishing a Vision-Language Model (VLM) with strong instruction-following capabilities for Web GUI tasks. 2) Online Agentic RL in the Wild: We develop an online interaction environment and fine-tune the VLM using a specialized RL pipeline. We introduce a Hybrid Reward Mechanism that combines a ground-truth-agnostic WebJudge for holistic outcome assessment with a Rule-based Decision Tree (RDT) for progress reward. This system effectively mitigates the credit assignment challenge in long-horizon navigation. Notably, our RL-enhanced model achieves a 38.1\% success rate (pass@5) on WebArena, outperforming all existing monolithic baselines. 3) Operator Agent: We introduce a modular agentic framework, namely \textbf{OpAgent}, orchestrating a Planner, Grounder, Reflector, and Summarizer. This synergy enables robust error recovery and self-correction, elevating the agent's performance to a new State-of-the-Art (SOTA) success rate of \textbf{71.6\%}.