每天知道
你的领域
出了什么

Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, overlooking physiological dynamics such as muscle mechanics and often modeling actions as monolithic patterns. These limitations hinder fine-grained, biomechanically grounded feedback. We introduce MyoMechanix, a multimodal ecosystem for weight-loaded actions that aligns motion with muscle activity. Expert-annotated, it contains 7,500+ samples of 20 actions from 38 subjects, with synchronized multiview RGB video, 3D pose, sEMG, and additional physiological signals, forming the largest multimodal AQA benchmark to date. We further construct the Fitness Knowledge Graph (FKG), which organizes expert annotations into structured relationships among actions, phases, key steps, errors, and corrective feedback, enabling compositional scoring and interpretable assessment. Building on these representations, we develop CUBIST (Compositional Ontological Reasoning Engine), which performs decomposition-analysis-recomposition for fine-grained error attribution and feedback generation. We also establish MyoMechanix-AQA, MyoMechanix-VideoQA, and a novel MyoMechanix-Video2EMG task. Experiments show that multimodal sensing and structured representations improve performance, interpretability, and error attribution, with CUBIST achieving state-of-the-art results; VideoQA enhances language-grounded action understanding; and Video2EMG suggests video-based alternatives to costly EMG sensing. MyoMechanix advances skilled activity understanding toward biomechanically grounded, multimodal, and compositional reasoning for Physical AI applications in fitness, rehabilitation, healthcare, and machine learning. Project page: https://haoyin116.github.io/MyoMechanix/

Vision-Language-Action (VLA) policies have advanced language-conditioned robotic manipulation, yet action-imitation objectives provide only weak supervision for metric 3D structure and short-horizon physical evolution. Geometry-enhanced policies mainly improve current-scene grounding, whereas predictive policies often model future dynamics in RGB or latent spaces and may incur substantial deployment cost. GaussianDream demonstrates that training-time current Gaussian reconstruction and future Gaussian prediction provide effective 3D supervision, but its dense VGGT/TGE-based prefix jointly carries state, dynamics, and action-conditioning information. We present \methodname, a compact, policy-native extension that inserts World State Tokens and World Prediction Tokens directly into the VLA backbone. A training-only World Representation Head decodes these tokens into a Current World and coupled Future Prediction over shared Gaussian primitives, while static--dynamic factorization preserves persistent structure and focuses residual motion on interaction-relevant regions. At inference, the head, renderer, auxiliary objectives, and VGGT/TGE pathway are removed, leaving only 20 world tokens without online Gaussian decoding or rollout. \method achieves 98.6% on LIBERO and 87.8% on LIBERO-Plus, with clear gains under Camera and Layout shifts. Real-robot experiments further improve average success from 29.2% to 52.5% over reproduced $π_{0.5}$ while maintaining efficient closed-loop control.

Vision-language-action (VLA) models provide a scalable path toward generalist robotic manipulation by integrating visual perception, language understanding, and continuous action control. However, we reveal a critical limitation of VLA architectures: the action expert has limited access to the 3D geometric and 2D semantic information available in VLM features. This accessibility gap weakens perceptual grounding and limits performance on fine-grained robotic manipulation. To address this issue, we propose V-Link, which explicitly recovers visual representations during the vision-language (VL) to action (A) feature transfer. Specifically, V-Link learns complementary Spatial and Semantic Query representations within the VLM and injects them into Action DiT through asymmetric pathways. Semantic Queries complement the original VLM image tokens, whereas Spatial Queries provide dedicated geometric conditioning for spatially grounded action generation. Across LIBERO, LIBERO-Plus, and RoboTwin 2.0, our V-Link improves the average success rate over base model GR00T N1.6 by +1.9%, +31.2%, and +18.8%, respectively. On the AGIBOT A3 Ultra, V-Link further achieves gains of +20% and +24% on two real-world humanoid tasks.

Bimanual manipulation in cluttered, contact-rich environments remains challenging because it requires coordinated motion generation, interaction-aware planning, and reliable execution under tight kinematic constraints. We present PRISM, a projection-integrated sampling-based Model Predictive Control (MPC) framework that uses a GPU-accelerated physics simulator as an online world model for complex dual-arm manipulation. The main algorithmic contribution is a QP-guided control sampling strategy that decouples trajectory exploration from kinematic feasibility. At each MPC step, sampled joint-velocity trajectories are projected onto the set of motions satisfying joint position, velocity, acceleration, and jerk bounds, together with an initial-velocity boundary condition, before rollout evaluation. This enables broad yet feasible exploration of coordinated bimanual behaviors. To support efficient online execution, we derive a custom ADMM/Bregman-splitting QP solver that exploits joint-wise separability and reusable matrix factorizations. We further use Bayesian optimization to tune task-cost weights offline, reducing manual parameter selection. We evaluate PRISM on challenging variants of PerAct$^{2}$ tasks, including obstacle-constrained ball transport, tray transport, cube handover, and box lifting. Experiments show improved robustness and task success relative to representative sampling-based baselines, while maintaining real-time or near-real-time execution. We also demonstrate successful sim-to-real transfer on dual UR5e manipulators, highlighting the practical potential of physics-based online planning for contact-rich bimanual manipulation. Project details, including code and supplementary videos, are available at \href{https://sites.google.com/view/prismbimanual}{https://sites.google.com/view/prismbimanual}.

A common strategy for scaling world models is to train on more crawled video with more compute. We argue that this strategy is inefficient: scaling world models also requires a recursive data engine that offers grounded reward signals. The success of code agents illustrates why this matters. As code is executable, compilers and runtimes can provide high-quality rewards for Reinforcement Learning (RL) post-training of LLMs. By contrast, spatial generation still relies largely on fuzzy proxies such as CLIP scores. These signals are fuzzy and biased, making them hard to support RL post-training. Compared with these, game development provides a missing reward environment for spatial world models. A scene encoded by a game engine is an executable world specification: the engine can efficiently check collision, physics, navigability and bounded playability, while the developer provides the global verification signal by judging whether the scene should be accepted. Game development also provides real-world long-horizon trajectory data for RL post-training. We therefore propose Reinforcement Learning with Human-Engine Verification (RLHEV), a post-training paradigm that combines dense engine signals with implicit human acceptance feedback from the development process.

Using conditional image generators, texture artists can explore many single-view looks for an existing 3D shape. Despite impressive progress, state-of-the-art generative methods still struggle to generate a full object texture while closely adhering to fine scale geometric detail and single view references, leaving little room for artists guidance. Furthermore, current automatic models lack the flexibility for artist to explore multiple textures from varied sources in an interactive and controllable manner. Unlike methods trained on large 3D datasets that generate full object textures from global guidance, our work explores a local and less data-hungry approach to texture with explicit artist control. We leverage the geometric self-similarity and geometry-texture correlation existing in many natural and man-made shapes; and train a shape-specific local texture generation and completion model. This model learns from existing image model priors and a single 3D shape, and is guided by attending to a set of geometry-aware reference patches. The trained shape-specific network can transfer any novel reference to the full target object texture through patchwise inpainting. We show improved or comparable quality to strong image-conditioned texture generation baselines, suggesting local texturing as a promising research direction. Our model also enables local geometry-conditioned texture inpainting, guided by artist-selected references, and generalizes to PBR materials and unseen meshes for texture transfer. We piloted our novel texture fill capability as a Blender addon with several 3D texturing professionals who reported positive feedback on the model's controllability, practical usefulness, and creative affordances.

Practical video editing is not only pixel generation: an editor must turn a brief, a clip pool, music metadata, and hard constraints into an executable timeline. We study this decision layer as executable video-editing planning and introduce RefineCut, which, unlike workflow systems that wrap a prompted frontier model, trains a compact open-weight planner for it. The planner edits a typed timeline through structured patches covering clip selection, trimming, ordering, transitions, and duration and music alignment; a deterministic verifier applies each patch and checks it against an explicit constraint ledger. Because editing has no single ground-truth repair, we do not imitate teachers directly: RefineCut replays every multi-teacher branch through the verifier and keeps verifier-best repairs as supervision. A second stage, RefineCut-Evo, lets the student score its own repairs with the verifier and a task rubric and trains on high-margin preference pairs, so the final $8$B planner runs in a closed verifier loop with no teacher calls at inference. On RefineCut-Bench ($3{,}578$ tasks, $7{,}971$ captioned clips, $499$ music tracks, explicit ledgers), verifier-replayed distillation lifts the planner from $0.620$ to $0.858$ on the protocol-specific Video-Editing Score and RefineCut-Evo reaches $0.924$; the gain transfers to Llama-3.1-8B and GLM-4-9B, and in the same closed loop the $8$B planner matches or exceeds its frontier teachers. Code and RefineCut-Bench are publicly released; see the Data Availability statement.

We present RoofDiT, a generative framework for 2D roof graph synthesis and reconstruction. Roofs are compactly described as planar graphs of junctions and structural edges, but existing methods often rely on fixed geometric rules or direct reconstruction objectives. RoofDiT instead models roof structures directly as vertex-edge graphs and learns a conditional generative prior over their geometry and connectivity. Our framework follows a two-stage design: a diffusion transformer generates roof vertices, and an edge prediction module infers the corresponding graph topology. To improve geometric fidelity, RoofDiT combines relative geometry-aware attention with footprint and aerial-image conditioning, while using an alignment regularizer to encourage common horizontal, vertical, and diagonal roof patterns. The same model supports unconditional generation, footprint-conditioned synthesis, and image-guided reconstruction by changing the conditioning signal. Experiments show improved graph generation quality over a diffusion baseline, favorable performance against a straight-skeleton prior in the footprint-conditioned setting, and the highest edge F1 among compared methods for image-guided reconstruction.

World models aim to simulate how complex environments evolve under actions and events, yet existing video-based world models primarily learn dynamics from visual observations, which reveal outcomes rather than the underlying knowledge, rules, and mechanisms governing world evolution. This makes it difficult to maintain persistent consequences and support coherent, open-ended evolution. We introduce Code World Model, a framework that separates world evolution from visual realization by combining the reasoning and coding capabilities of language models with the generative priors of video models. A coding agent serves as the world brain, reasoning about events and their consequences and generating executable code to maintain persistent world state and perform rule-consistent evolution. To connect executable state with visual generation, we introduce a proxy representation that encodes frame-wise spatiotemporal constraints and is compiled into a proxy video, which conditions a video model to render high-fidelity visual observations. We further develop data pipelines for constructing aligned proxy-observation pairs from gameplay and real-world videos. After fine-tuning on paired gameplay data, MiniMax-H3 follows proxy-based spatiotemporal specifications from simple interactive worlds built by the coding agent while preserving rich visual details and dynamics. These results demonstrate the potential of combining code for persistent world evolution with video models for flexible visual realization, providing a new path toward open-ended world models.

*Chulin Zhao and Ruoqi Hu contributed equally to this work. State-of-the-art text-to-image (T2I) models exhibit pronounced and systematic defects when prompts involve intricate compositional factors such as multiple entities and multiple attributes. In this paper, we investigate how humans identify such defects. Specifically, we manually select 651 reference images from the four categories of people, hand, object, and scene that exhibit complex compositional characteristics, from which prompts emphasizing compositional factors are derived by manually editing ChatGPT-generated prompts. We then feed the prompts into three selected T2I models to generate AI images and conduct a comprehensive subjective study to identify their defects. For each image, 29 participants provide multi-label assessments specifying defect types and locations. The study yields the compositional AI-generated image defect (CO-AID) dataset, including reference images, prompts, AI-generated images, and information on defect locations and types. Experimental results show that training a deep model on CO-AID can both predict defects in AI-generated images and optimize AI image generation, demonstrating its usability and effectiveness. The database and supplementary materials are available at: https://github.com/Future-IQA/CO-AID .

Recent advances in video editing have been largely driven by large-scale instruction-based datasets. However, existing datasets still suffer from two critical limitations. First, target videos are commonly produced by automatic editing models, which may introduce visible artifacts and unreliable supervision signals. Second, most public datasets rely primarily on textual instructions, while lacking visual references that are crucial for precise, identity-preserving, and controllable editing. To address these limitations, we introduce RefVideo-6M, a large-scale reference-guided editing dataset containing 5 million video editing samples and 1 million image editing samples. To ensure reliable supervision, our dataset uses a construction pipeline that treats artifact-free real videos as editing targets and generates quality-filtered input conditions with multiple editing experts. In addition, it provides approximately 6 million visual references, covering diverse reference types and editing scenarios, thereby enabling models to learn fine-grained visual correspondence beyond text-only instructions. Based on RefVideo-6M, we further train a reference-guided video editing model, Ref-MoT, to evaluate the effectiveness and scalability of the proposed dataset. Extensive experiments demonstrate that RefVideo-6M provides substantially more reliable supervision than existing datasets and enables the training of powerful editing models with improved visual quality, controllability, and reference consistency. The open-source dataset is available at https://huggingface.co/datasets/RefVideo6M/RefVideo6M.

Generative video models now synthesize footage nearly indistinguishable from reality. Their promise as interactive tools hinges on fine-grained control of how objects and the camera move over time, yet each existing approach captures only part of this: camera-parameter methods steer the viewpoint but cannot move objects, 2D-trajectory methods act in the image plane and ignore depth and occlusion, and recent 3D methods add geometry but run only offline at a fixed length. In particular, none combines 3D-consistent control of both camera and objects with real-time, streaming generation. Here we show that camera motion, object trajectories, and depth can be unified into a single 3D point-track representation, from which one model performs joint camera and object control, depth editing, and motion transfer in a single forward pass. To learn this interface at scale, we mine in-the-wild video for 3D motion supervision, yielding OpenVidHD-Motion3D, and encode it with a lightweight Geometric Motion Head that plugs into a pretrained video diffusion model. Because this encoder is temporally separable, we distill the model into a causal streaming student that generates arbitrarily long video in four denoising steps at memory independent of length. This unified design surpasses prior camera-only, 2D, and offline-3D methods in motion-control precision while covering modalities they address only in isolation. 4DStreamCtrl runs at 20 FPS on a single high-end GPU for 480p video and stays temporally coherent over hundreds of frames, enabling, to our knowledge, interactive 4D-controllable streaming generation for the first time. More broadly, grounding generation in explicit 3D geometry with efficient causal inference points toward interactive world models with closed-loop spatiotemporal control, from controllable simulators to real-time visual imagination for embodied agents.

Open-ended Theory-of-Mind (ToM) trackers emit valid beliefs absent from finite references. A finite-reference-plus-matcher pipeline marks unmatched outputs false, creating proxy labels that can reverse proper-score model selection on fixed outputs. Holding 259 beliefs and paired scores fixed, reference recoding lowers weighted prevalence from 0.783 to 0.295 and reverses strictly proper Brier risk: a frozen source-prior rule leads native confidence by 0.227 under reference labels and trails by 0.152 under blinded adjudication, in all six authored scenarios. A reference-only Platt recalibrator reverses further. An ICE-specific reversal appears in a released 301-question NQ-open DPR-BERT pipeline: its average-confidence baseline improves instance-level calibration error by 0.045 under exact match but worsens it by 0.074 under human correctness, with both intervals excluding zero. On independently authored OpenToM narratives, 90-96% of audited unmatched beliefs are literally true and the paired direction again reverses. An exact decomposition attributes the distortion to omitted truths, and a closed-form criterion correctly classifies comparisons from twelve released systems. Frozen-audit retrospective replay shows 50 attempted annotations recover ranking direction with probability at least 0.996. TriSource-Restore anchors full-frame reference labels and frozen automatic judgments to a probability-sampled human pilot, maintains at least nominal coverage, narrows intervals, and repairs confidence subject to a base-rate deployment gate.

Co-speech gesture generation has made significant progress toward realistic full-body motion from speaker audio, yet existing models lack fine-grained spatial controllability of individual joints. To address this, we introduce InteractGesture, a model-agnostic, inference-time method for spatially controllable gesture generation. InteractGesture guides target latent estimates of a diffusion sampler through a differentiable RVQ-VAE decoder, backpropagating spatial control gradients to adjust motion latents during sampling. A primary challenge in streaming co-speech generation is chunk-wise dependency: standard sequential inference freezes prior chunks, preventing spatial constraints in future chunks from adjusting preceding trajectories and causing boundary inconsistencies. To overcome this limitation, we propose Progressive Chunk Guidance, a chunk-window strategy that maintains an active set of editable chunk latents with staggered delays, enabling spatial constraints to propagate gradients backward across chunk boundaries during streaming generation. Experiments on the BEAT2 dataset show that InteractGesture improves multi-joint spatial control while preserving overall gesture quality. Furthermore, our approach supports diverse applications, including sparse joint positioning, dense joint trajectory control, and directional pointing. Our project page is available at https://exitudio.github.io/interactgesture-page .

Dynamic contrast-enhanced breast MRI is central to cancer diagnosis and monitoring, but requires gadolinium-based contrast agents. In this work, we address pre-to-post contrast breast MRI synthesis for the MAMA-SYNTH challenge. We propose MAMA-FLUX.2, a conditional latent flow-matching approach based on FLUX.2-Klein-4B. The pre-contrast image is encoded as spatial conditioning, while the model predicts the flow field associated with the post-contrast target latent. To adapt the pretrained model efficiently, we use LoRA fine-tuning and introduce a regional training objective combining global flow matching, tumor-region supervision, and stable foreground regularization. We further investigate LoRA rank, intensity windowing, and regional loss weights on axial slices, prioritizing clinically relevant tumor-focused metrics. Our ablation study shows that moderate tumor and stable-foreground weighting improves the trade-off between image fidelity and tumor-region accuracy. The final model achieves the best overall balance with LoRA rank/$α=64/64$, $\mathrm{MHA}_{\max}=25$, $λ_{\mathrm{tumor}}=0.25$, and $λ_{\mathrm{stable}}=0.1$. These results demonstrate that compact pretrained rectified-flow transformers can be adapted for contrast-enhanced MRI synthesis using parameter-efficient fine-tuning and task-aware regional losses.

Forecasting a stochastic dynamical system rarely means a single number: one wants several observables---future state, threshold event, regime label---each with its own likelihood. Standard multi-task recipes balance per-task losses, tuned or learned. We instead compose the observables' likelihoods in per-task free-routed last-layer beliefs on a shared backbone; this absorbs unit-dependent loss scaling into likelihood parameters learned in the same gradient pass. Stochastic dynamics supply what static benchmarks cannot: computable ground truth for the predictive variance. Results land where theory puts them: on the well-specified, homoscedastic Ornstein--Uhlenbeck process the learned predictive law recovers the analytic kernel and correctly specified baselines tie. On heteroscedastic systems (stochastic Lorenz-63, real air-quality data) the belief's input-dependent variance separates: best single-run NLL on the state and regime tasks, calibration matched only by arms whose NLL it beats, at a fraction of the tuned grids' cost. On the real series the state margin holds across five rolling origins.

Physical human-robot collaboration requires a robot to provide assistance when human intention is clear while remaining compliant when several future motions are plausible. We present an adaptive stiffness framework based on generative action-chunk sampling. Conditioned on an RGB image and external joint-torque estimates, the policy samples multiple future action chunks from an observation-conditioned prior. Variation among the sampled action chunks is used to continuously adapt joint stiffness and damping. Greater variation makes the robot more compliant to facilitate human guidance, whereas lower variation provides firmer assistance. In a real-world collaborative transport task with four possible directions, the proposed method achieved an average success rate of 0.95, compared with 0.83 for a fixed-stiffness ablation and 0.69 for a deterministic baseline. Near direction determination, variation among the sampled action chunks increased and the controller accordingly reduced stiffness. These results suggest that variation among actions sampled by a generative policy can serve as an online control signal for balancing assistance and compliance in physical human-robot interaction.

Multinomial choice models allow flexible substitution patterns but become computationally demanding with many alternatives or observations. With a fixed per-observation simulation budget, simulated maximum likelihood introduces simulation bias, while each optimization step requires a full-sample likelihood evaluation. We propose Stochastic Approximation with Unbiased Simulated Scores (SAUSS), an averaged stochastic approximation based on conditionally unbiased mini-batch score estimates. Each iteration uses a fixed mini-batch regardless of sample size. For multinomial probit, accept-reject sampling provides exact conditional draws and unbiased score estimates for any fixed number of accepted draws. Under local conditions, asymptotic theory for the averaged estimator and the partial-sum process of the SAUSS iterates incorporates mini-batch and simulation variability and supports random-scaling and plug-in inference. In simulations and an application, SAUSS gives comparable results in less than 1% of the computation time of simulated maximum likelihood. SAUSS extends to limited dependent variable models with conditional-expectation score representations and exact conditional sampling.

Functional data analysis is an important statistical field that treats data as random functions. In practice, the random functions are often not fully observed but instead measured at discrete times. While simpler problems, such as mean and covariance estimation, have been widely studied for discretely observed data, optimal estimation of linear regression for this data type has remained unsolved for over two decades. To tackle this fundamental challenge, we propose a novel approach, referred to as pooling ridge estimation, which combines the advantages of pooling strategy and RKHS-based method by incorporating the unbiased estimation of operators based on discretely observed measurements from all subjects. This unified estimation framework enables us to achieve minimax optimality in prediction risk in arbitrary sampling schemes ranging from sparse to dense designs, for both scalar-on-function and function-on-function regression models. Such methodological and theoretical advances are obtained for the first time and accurately reveal the influence of discrete sampling. For scalar-on-function regression, the phase transition occurs once, separating the convergence behavior into two distinct regimes. Remarkably, for function-on-function regression, up to three phase transitions may occur, determined by the sampling frequencies of the predictor/response functions. Finally, simulation experiments and two real data examples provide empirical support for the proposed methods.

High-resolution precipitation fields are essential for hydrological impact assessment, yet global climate model outputs are too coarse and biased for direct use. AI-based statistical downscaling with diffusion models offers a promising approach, but the mechanism by which large-scale atmospheric predictors condition generation remains largely unexplored. We investigate three conditioning strategies for a denoising diffusion probabilistic model applied to daily precipitation downscaling: channel concatenation of upsampled coarse predictors, cross-attention conditioning with a learned convolutional encoder, and cross-attention conditioning with the frozen encoder of the pretrained Prithvi WxC weather foundation model. All strategies are evaluated against an unconditioned baseline under identical conditions using probabilistic, distributional, spectral, and extreme-event metrics for the Colorado River Basin. Concatenation conditioning achieves the lowest point-wise CRPS and MSE, but tends to produce over-smoothed fields that suppress high-intensity events. In contrast, cross-attention conditioning provides substantially better distributional realism and modest improvements in spectral fidelity. Improvements are greatest for extremes: the Prithvi-WxC conditioned model retains over half of >100mm/day events, although estimates are uncertain due to limited samples. When trained on the full dataset, the learned convolutional model performs similarly to the foundation model-conditioned approach while requiring lower computational resources. However, the Prithvi-WxC-conditioned model achieves comparable performance with only five years of training data. These results indicate that cross-attention conditioning offers advantages over simple concatenation for probabilistic precipitation downscaling, and that pre-trained foundation model representations may offer benefits in data-limited settings.

Motivated by parallel decoding in masked diffusion models, we study adaptive parallel sampling of discrete vectors: in each round, a deterministic policy selects unrevealed coordinates on the basis of the values observed so far, and the selected coordinates are sampled independently from their exact conditional marginals. Approximation error is measured by forward Kullback-Leibler divergence, and serial depth is the minimum target-averaged number of rounds meeting a prescribed error budget. Our central result is an exact identity: the divergence of every policy equals the expected conditional total correlation accumulated over its reveal rounds, so conditional total correlation is the exact information cost of within-round parallelism. The identity yields zero-error schedules for finite-order Markov chains with round complexity proportional to the Markov order and logarithmic in sequence length, a matching logarithmic characterization of the Bernoulli walk at every fixed error budget, and a linear-versus-logarithmic separation between left-to-right and hierarchical reveal orders. Uniform random permutations require linearly many expected rounds at every fixed budget; their hard-cap round-error tradeoff is an exact integer-composition problem whose fixed-round asymptotics and joint-scaling frontier we determine. Uniform balanced binary strings have depth of order squared logarithm, and binary one-hot blocks have square-root depth, with rectangular versions realizing every polynomial exponent up to one half. These results separate serial depth from entropy and negative log-likelihood, and establish conditional-dependence structure as a fundamental determinant of parallelizability. Experiments with a masked diffusion language model show that the pseudo-cost distinguishes deployed decoding rules and that its policy rankings agree closely with the quality of self-sampled outputs.

Deploying large language models for professional financial review requires more than measuring general financial competence: models must perform the specific review operation required by a workflow and determine whether available evidence is sufficient for a defensible decision. Existing financial benchmarks cover knowledge, reasoning, compliance, and professional tasks, but their evaluation units are often organized around datasets or task formulations rather than the decisions that deployed systems support. We introduce FinRiskAtlas, a Chinese-language benchmark that evaluates financial LLMs along two complementary dimensions: operation execution under fixed evidence states and evidence-state control under evolving review conditions. The static benchmark contains 9,742 instances across 53 task families, including 42 Domain Knowledge families and eleven downstream review operations defined by explicit evaluation contracts. FinRisk-Ask extends this framework through offline replay of 680 pre-action states from 104 de-identified professional trajectories, withholding future evidence during inference and using it only to construct expert-verified evidence targets. Across 33 model configurations, operation-level evaluation yields non-redundant rankings (mean pairwise Spearman correlation 0.42 across downstream operations), and knowledge-based shortlisting can incur up to 18.01 points of regret on individual operations. FinRisk-Ask further shows that entering the Ask branch more frequently does not necessarily improve request targeting or end-to-end evidence acquisition. These results show that broad financial capability scores do not fully capture where models are reliable in professional workflows, motivating evaluation units aligned with the decisions and evidence states that deployed systems must support.

Multimodal instruction-following models require training data that is accurate, diverse, verifiable, and challenging. Existing synthesis pipelines typically follow a one-pass generate-and-filter paradigm, discarding feedback from failed samples, verifier outcomes, and target-model errors. We present VISA (Visual Instruction Synthesis Agent), an agentic framework that reformulates multimodal instruction synthesis as a self-evolving loop. At each round, VISA analyzes an image to filter incompatible constraints and discover new verifiable ones, samples diversity- and difficulty-aware constraint sets from persistent memory, generates candidate instructions, and verifies the resulting samples with executable tools and structured large language model judges. Failed samples trigger diagnostic-guided recovery, while accepted samples are probed against the target model to estimate difficulty. The resulting verifier signals and target-model failure profiles are written back to memory, allowing subsequent rounds to adaptively expand the constraint space, reduce template repetition, and focus on unresolved model weaknesses. The same verifier contracts further provide reward signals for reinforcement learning without a separately trained reward model. Experiments on MM-IFEval show that VISA consistently improves multimodal instruction following over strong baselines, while preserving general multimodal capability across seven public benchmarks.

Answer accuracy is an insufficient reliability signal for LLM data agents. In structured-data tasks, a benchmark-correct answer can be produced by an invalid trace. This paper introduces Trace Integrity, a deployment reliability criterion for evaluating whether the computation recorded behind an answer is explicit, executable, schema-valid, operator-faithful, replayable, answer-consistent, and auditable. We identify the Structure Gap as the deployment failure mode that makes Trace Integrity necessary: natural-language reasoning and free-form rationales do not reliably specify the operator-level programs required by real-world systems. We operationalize Trace Integrity with execution contracts, structured artifacts that bind user intent to schema elements, operator plans, assumptions, executable queries, verification status, and final-answer linkage. We also introduce CAIT (Correct Answer / Invalid Trace) Rate, which measures how often answer-only evaluation counts computationally unsupported outputs as successes. In an empirical demonstration on BIRD Mini-Dev, Direct SQL, Operation Summary + SQL, and Contract-First SQL achieve answer accuracies of 20%, 22%, and 24%, while their Trace Integrity Pass Rates are 39%, 43%, and 40% and their CAIT Rates remain high at 55%, 59.1%, and 45.8%, showing that answer accuracy, trace validity, and silent-failure risk are distinct evaluation signals. Real-world LLM data agents should, therefore, be evaluated not only by whether their outputs match a reference answer, but by whether those outputs are backed by auditable computation.

Automated root cause analysis (RCA) with large language models (LLMs) has drawn growing attention. Today, SREs typically automate RCA with LLMs in one of two ways: directly using a general-purpose agent (e.g., Codex or Claude Code) for diagnosis, or building a specialized RCA agent from scratch. As mainstream general agents grow more capable and iterate quickly, our quantitative study finds that the former now often surpasses the latter. Its accuracy, however, still falls short of production needs, and this gap stems mainly from the external adaptation layer outside the agent's general capabilities, namely the harness. We therefore argue that LLM-based RCA should focus on this external harness, reusing the strong general capabilities of a modern agent rather than rebuilding an agent from scratch. A key capability of such a harness is to self-evolve, accumulating system-specific experience from past diagnoses so that it gets better the more it is used. We introduce OpsHarness, a self-evolving RCA harness that turns diagnosis experience into reusable expertise. Its data plane combines layered operational knowledge with an idea-card tool library, while its control plane coordinates setup, diagnosis, evolution, and verification. During evolution, OpsHarness contrasts successful and failed trajectories, converts their evidence into atomic proposals, and admits updates only through a dual-gate verification process designed to prevent overfitting and regression. Across two public benchmarks and an industrial deployment, OpsHarness achieves 59.0% top-1 accuracy, improving over a bare general agent by 63.4% and over baseline RCA agents by 4.02$\times$.

Self-evolving LLM coding agents write their own tools by imitating retrieved skills from shared skill libraries. We identify a vulnerability in this loop: during authoring, a retrieved malicious skill can become the template for a new skill that preserves the payload. We call this self-poisoning: the agent authors, stores, and runs the resulting malicious skill. We exploit it through EvoMal, an attack that amplifies self-poisoning by wrapping an interchangeable payload in a banner, a set of benign-looking structural elements that induces an imitating agent to reproduce the enclosed code. The attacker plants malicious skills in the library without invoking them. The agent then authors and executes new skills carrying the harmful code. Each authored copy can re-enter the library and be imitated again, forming a self-propagating worm that persists after the planted skills are removed. We define the agent self-poisoning rate (ASPR) as the fraction of tasks that add a newly authored malicious skill to the library. Across six models on 153 tool-relevant SWE-bench Verified tasks, ASPR ranges from 20.3% to 41.8%, and the poisoned libraries hold 4.9 to 9.0 times as many malicious skills as were planted. The vulnerability also appears without a banner: DeepSeek-V4-Pro reaches 11.1% ASPR with the payload alone. Tailoring the planted skill descriptions to one task family raises ASPR to 86.7%. After the planted skills are removed, Qwen3 retains a round-5 ASPR of 68% because agent-authored copies remain. These copies evade existing defenses, which focus on attacker-submitted names, code, and signatures. We propose counter-prompt, a defense that discourages banner-style copying and reduces EvoMal's ASPR to at most 6.7% with no significant task-completion loss.

Agentic coding workflows are now widely deployed in real-world systems. With long-horizon reasoning and tool use, token usage has become an important consideration for both cost and efficiency. Two engineers using AI will solve the same problem differently. How the specification of a task shapes an agent's token spend, and whether that spend can be predicted in advance, are open questions. Here, we study the effects of different task specifications on agentic token spend with the Kimi K3 model at three thinking efforts. Across $2,700$ runs, we show that reducing a full task specification to a bare user story raises token spend by $29.7%$, while run-to-run variance remains unaffected by any prompt changes. We show that prompt-sensitivity is task-dependent, running from $13%$ to $115%$. We fit a simple predictor that can price a full distribution of task specifications and thinking effort configurations from a single cheap probe on an unseen task within $36%$, improving over prior work in predicting token spend. Our work provides initial results quantifying the effects of task specification on agentic token spend and introduces a method that can be used to systematically evaluate the cost of AI coding workflows.

Large language models write correct code for isolated problems but remain far weaker at autonomous machine-learning development, where an agent must revise data pipelines, models, and validation over hours of feedback, and on most competitions still finishes below strong human competitors. Outcome-based benchmarks record this gap but not its cause, because they grade the final submission and discard the development process behind it. We introduce TraceML, which pairs human and agent work on the same competitions under one version-level schema: 4,465 human Kaggle trajectories across 134 competitions, seven of which are also worked by two agent scaffolds, giving 430 paired human and 207 agent trajectories. Every code version carries its score, its timestamp, and labels for the action taken, its intent, the edit size, and the score effect. Read this way, the gap becomes concrete. Experts alternate data work, validation, model changes, and ensembling, and return to approaches they had set aside. Each agent scaffold instead collapses into a narrow loop: Codex spends its steps re-weighting ensembles and tuning submissions, MLEvolve mutates its model in place, and neither pivots at the human rate nor reopens abandoned work. A short planning prompt distilled from human practice moves the behaviors it names toward the human profile and lifts scores, but the effort profile stays agent-shaped: instruction closes only the part of the gap that reduces to instructions. We release the corpus, the schema, the labelers, and the extraction pipeline at https://huggingface.co/datasets/jerryyan/TraceML.

Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying foundation model. Yet harness design remains manual, task-specific, and fundamentally unscalable. We present JIT-Agent, a harness intelligence model trained to synthesize task-adaptive agent harnesses on the fly for arbitrary off-the-shelf agentic LLMs. We formalize the agent harness as a composable, machine-generatable artifact governed by a fixed four-module protocol, and train JIT-Agent to customize harnesses for a given task at hand, repair harnesses for stable and reliable execution, and self-evolve by distilling performance signals from an expanding archive of prior harness configurations. Equipped with JIT-Agent as a harness helper, DeepSeek-V4-Flash surpasses GPT-5.6 on DeepSearchQA (+9.1) and OdysseyBench (+4.3), while the already strong GLM-5.2 gains up to +20.2 points. Across controlled evaluations, JIT-Agent-generated harnesses are performance-competitive with mature agent runtimes such as OpenCode and Claude Code and consistently improve multi-scale model families of DeepSeek V4, Mimo-V2.5, and Qwen3.6. To our knowledge, JIT-Agent is the first model purpose-built for just-in-time harness generation, establishing harness intelligence as a trainable, transferable, and compounding dimension of agent capability orthogonal to model scaling.

Federated Learning (FL) enables distributed training of machine learning models while preserving data privacy. However, FL struggles with heterogeneous, non-IID client data distributions, resulting in sub-optimal and biased global models. In this paper, we propose pFedMARL, a novel approach leveraging Multi-Agent Reinforcement Learning (MARL) with Twin Delayed Deep Deterministic Policy Gradient (TD3) to dynamically adapt aggregation strategies in FL settings. Our method employs a server-side agent adjusting client contributions to optimize global model robustness and client-side agents balancing global and local updates to personalize models effectively without pre-training. We demonstrate superior performance of pFedMARL for training a semi-supervised audio spectrogram transformer, matching or outperforming FedAvg, Ditto, and local training approaches across multiple non-IID scenarios and in the presence of adversarial clients. Our results indicate that pFedMARL actively improves accuracy, robustness, and fairness, making it suitable for real-world deployments.