Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains one of the most labor-intensive parts of paper preparation. Existing automated systems each target a single figure type under text-only input, leaving the diversity of types and conditions researchers actually use unaddressed; their raster outputs further cannot be locally revised. Because scientific figures are structured compositions of discrete semantic components, the localized errors generators produce on such layouts demand not a stronger backbone but a harness. We instantiate this harness in two complementary systems: Crafter, a multi-agent harness for figure generation that generalizes across figure types and input conditions without architectural changes, and CraftEditor, which applies the same pattern to convert raster outputs into editable SVGs. Moreover, we introduce CraftBench, a benchmark spanning three figure types and four input conditions with human quality annotation. Experiments show that Crafter substantially outperforms both standalone generators and the agentic baseline on PaperBanana-Bench and CraftBench, with ablations confirming each component's independent contribution; CraftEditor faithfully converts outputs into editable SVGs that surpass all baselines. Our code and benchmark are available at https://github.com/HaozheZhao/Crafter.

SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution

State space models (SSMs) have emerged as a powerful paradigm for efficient single-image super-resolution (SR) due to their linear complexity and long-range modeling capabilities. However, existing Mamba-based methods typically rely on data-agnostic rigid scanning, which reshapes 2D images into 1D sequences over a fixed grid, inevitably disrupting spatial-semantic topology and introducing artifacts. Inspired by the \textbf{Gestalt perceptual grouping theory}, we propose \textbf{SP-MoMamba}, a superpixel-driven mixture of state space experts designed for content-aware SR. Our core idea is to transform the traditional rigid scanning into a \textbf{semantic-level interaction} by treating superpixels as fundamental units. Specifically, we introduce the \textbf{Superpixel-driven State Space Model (SP-SSM)}, which compresses semantically homogeneous regions into high-order tokens to preserve global topological consistency. To address the conflict between fixed scanning scales and diverse semantic granularities, we develop the \textbf{Multi-Scale Superpixel Mixture of State Space Experts (MSS-MoE)}. This module utilizes a dynamic routing mechanism to adaptively assign scale-specific experts, effectively capturing multi-scale textures while reducing computational redundancy. Furthermore, to prevent the loss of high-frequency details during global abstraction, we introduce a \textbf{Local Spatial Modulation Expert (LSME)} to complement the global modeling, ensuring a precise reconstruction of sharp edges and fine structures. Extensive experiments on standard benchmarks demonstrate that SP-MoMamba achieves superior reconstruction fidelity and a more favorable efficiency-performance trade-off compared to state-of-the-art efficient SR methods.

EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions

Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This leaves out a basic question: can an agent keep its own codebase working as requirements change? We introduce EvoCode-Bench, a benchmark of 26 stateful coding tasks and 227 evaluated rounds. Each task preserves the agent's workspace for 5-15 rounds, states requirements through observable behavior, and uses cumulative executable tests to check new requirements and still-active prior ones. We evaluate 13 coding agents with two metrics: MT@4, a four-attempt fail-stop multi-round score, and SR, a single-round score from a reference-completed prior state. For most agents, SR exceeds MT@4 by 22-40 points. The gap also changes rankings: the highest-SR agent (78.9) ranks only third in persistent execution (44.0 MT@4). Even the strongest agents achieve only about 50% success on multi-turn metrics, and aggregate pass rate drops below half of round-1 performance by round 5. Failure analysis shows tier-dependent behavior: weaker agents fail early, while stronger agents survive long enough to expose specification-tracking and regression failures. We release the benchmark data and Harbor multi-turn infrastructure.

Variational Matrix-Learning Fourier Networks for Parametric Multiphysics Surrogates

Multiphysics simulation is critical for system-technology co-optimization (STCO) in chiplet-based design, but repeated finite-element solutions of PDE-governed problems are computationally expensive in parametric design exploration. This paper proposes a variational matrix-learning Fourier network (VMLFN) for efficient parametric multiphysics surrogate modeling. VMLFN constructs a log-space sine neural representation with randomly sampled spectral frequencies, frequency-dependent decay regulation, and embedded Dirichlet boundary conditions. With fixed hidden-layer parameters, the output-layer weights are determined by reformulating the governing PDEs into variational weak forms and enforcing the stationarity condition of the resulting energy functional. This converts physics-informed training into a linear matrix-solving problem, requiring only first-order derivatives and avoiding both high-order automatic differentiation and penalty-coefficient tuning. A heuristic frequency-scanning algorithm is further introduced to select a problem-adaptive maximum frequency that covers the dominant spectral range of the target problem. The proposed method is validated on heat conduction, solid mechanics, and Helmholtz wave propagation problems. Results from five benchmark cases demonstrate that VMLFN delivers accurate full-field predictions with substantial speedup over conventional physics-informed neural networks and repeated finite-element simulations.

A geometry aware framework enhances noninvasive mapping of whole human brain dynamics

Non-invasive electrophysiology lacks methods that accurately reconstruct whole-brain spatiotemporal dynamics while incorporating individual cortical geometry, leaving current electroencephalography and magnetoencephalography source imaging limited by simplistic or biologically implausible priors. Here, we show that embedding participant-specific Geometric Basis Functions (GBFs), eigenmodes derived from each individual's cortical surface, provides a powerful anatomic constraint that resolves the inverse problem and improves reconstruction fidelity. The method reconstructs neural sources as linear combinations of geometric basis functions, thereby aligning source estimates with the geometric organization of neural dynamics. We validate GBF across the Meta-Source Benchmark, task-evoked data, resting-state networks, intracranial stimulation, and epilepsy data. The results demonstrate that GBF yields high localization accuracy and captures fast spatiotemporal dynamics consistent with anatomical pathways. These findings suggest that both spontaneous and evoked whole-brain activity can be described by hundreds of geometric modes, providing a compact yet accurate representation of neural sources. By linking cortical geometry to electrophysiological dynamics, GBF offers a versatile source imaging tool for both scientific and clinical applications.

ClawBench: Can AI Agents Complete Everyday Online Tasks?

AI agents may be able to automate your inbox, but can they automate other routine aspects of your life? Everyday online tasks offer a realistic yet unsolved testbed for evaluating the next generation of AI agents. To this end, we introduce ClawBench, an evaluation framework of 153 simple tasks that people need to accomplish regularly in their lives and work, spanning 144 live platforms across 15 categories, from completing purchases and booking appointments to submitting job applications. These tasks require demanding capabilities beyond existing benchmarks, such as obtaining relevant information from user-provided documents, navigating multi-step workflows across diverse platforms, and write-heavy operations like filling in many detailed forms correctly. Unlike existing benchmarks that evaluate agents in offline sandboxes with static pages, ClawBench operates on production websites, preserving the full complexity, dynamic nature, and challenges of real-world web interaction. A lightweight interception layer captures and blocks only the final submission request, ensuring safe evaluation without real-world side effects. Our evaluations of 7 frontier models show that both proprietary and open-source models can complete only a small portion of these tasks. For example, Claude Sonnet 4.6 achieves only 33.3%. Progress on ClawBench brings us closer to AI agents that can function as reliable general-purpose assistants.

Towards unified brain-to-text decoding across speech production and perception

Speech production and perception are the main ways humans communicate daily. Prior brain-to-text decoding studies have largely focused on a single modality and alphabetic languages. Here, we present a unified brain-to-sentence decoding framework for both speech production and perception in Mandarin Chinese. The framework exhibits strong generalization ability, enabling sentence-level decoding when trained only on single-character data and supporting characters and syllables unseen during training. In addition, it allows direct and controlled comparison of neural dynamics across modalities. Mandarin speech is decoded by first classifying syllable components in Hanyu Pinyin, namely initials and finals, from neural signals, followed by a post-trained large language model (LLM) that maps sequences of toneless Pinyin syllables to Chinese sentences. To enhance LLM decoding, we designed a three-stage post-training and two-stage inference framework based on a 7-billion-parameter LLM, achieving overall performance that exceeds larger commercial LLMs with hundreds of billions of parameters or more. In addition, several characteristics were observed in Mandarin speech production and perception: speech production involved neural responses across broader cortical regions than auditory perception; channels responsive to both modalities exhibited similar activity patterns, with speech perception showing a temporal delay relative to production; and decoding performance was broadly comparable across hemispheres. Our work not only establishes the feasibility of a unified decoding framework but also provides insights into the neural characteristics of Mandarin speech production and perception. These advances contribute to brain-to-text decoding in logosyllabic languages and pave the way toward neural language decoding systems supporting multiple modalities.

AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines

The performance of autonomous Web GUI agents heavily relies on the quality and quantity of their training data. However, a fundamental bottleneck persists: collecting interaction trajectories from real-world websites is expensive and difficult to verify. The underlying state transitions are hidden, leading to reliance on inconsistent and costly external verifiers to evaluate step-level correctness. To address this, we propose AutoWebWorld, a novel framework for synthesizing controllable and verifiable web environments by modeling them as Finite State Machines (FSMs) and use coding agents to translate FSMs into interactive websites. Unlike real websites, where state transitions are implicit, AutoWebWorld explicitly defines all states, actions, and transition rules. This enables programmatic verification: action correctness is checked against predefined rules, and task success is confirmed by reaching a goal state in the FSM graph. AutoWebWorld enables a fully automated search-and-verify pipeline, generating over 11,663 verified trajectories from 29 diverse web environments at only $0.04 per trajectory. Training on this synthetic data significantly boosts real-world performance. Our 7B Web GUI agent outperforms all baselines within 15 steps on WebVoyager. Furthermore, we observe a clear scaling law: as the synthetic data volume increases, performance on WebVoyager and Online-Mind2Web consistently improves.

UI-Venus-1.5 Technical Report

GUI agents have emerged as a powerful paradigm for automating interactions in digital environments, yet achieving both broad generality and consistently strong task performance remains challenging.In this report, we present UI-Venus-1.5, a unified, end-to-end GUI Agent designed for robust real-world applications.The proposed model family comprises two dense variants (2B and 8B) and one mixture-of-experts variant (30B-A3B) to meet various downstream application scenarios.Compared to our previous version, UI-Venus-1.5 introduces three key technical advances: (1) a comprehensive Mid-Training stage leveraging 10 billion tokens across 30+ datasets to establish foundational GUI semantics; (2) Online Reinforcement Learning with full-trajectory rollouts, aligning training objectives with long-horizon, dynamic navigation in large-scale environments; and (3) a single unified GUI Agent constructed via Model Merging, which synthesizes domain-specific models (grounding, web, and mobile) into one cohesive checkpoint. Extensive evaluations demonstrate that UI-Venus-1.5 establishes new state-of-the-art performance on benchmarks such as ScreenSpot-Pro (69.6%), VenusBench-GD (75.0%), and AndroidWorld (77.6%), significantly outperforming previous strong baselines. In addition, UI-Venus-1.5 demonstrates robust navigation capabilities across a variety of Chinese mobile apps, effectively executing user instructions in real-world scenarios. Code: https://github.com/inclusionAI/UI-Venus; Model: https://huggingface.co/collections/inclusionAI/ui-venus

Kimi K2.5: Visual Agentic Intelligence

We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evaluations show that Kimi K2.5 achieves state-of-the-art results across various domains including coding, vision, reasoning, and agentic tasks. Agent Swarm also reduces latency by up to $4.5\times$ over single-agent baselines. We release the post-trained Kimi K2.5 model checkpoint to facilitate future research and real-world applications of agentic intelligence.