SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

We introduce SciEvalKit, a unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities. Unlike general-purpose evaluation platforms, SciEvalKit focuses on the core competencies of scientific intelligence, including Scientific Multimodal Perception, Scientific Multimodal Reasoning, Scientific Multimodal Understanding, Scientific Symbolic Reasoning, Scientific Code Generation, Science Hypothesis Generation and Scientific Knowledge Understanding. It supports six major scientific domains, spanning from physics and chemistry to astronomy and materials science. SciEvalKit builds a foundation of expert-grade scientific benchmarks, curated from real-world, domain-specific datasets, ensuring that tasks reflect authentic scientific challenges. The toolkit features a flexible, extensible evaluation pipeline that enables batch evaluation across models and datasets, supports custom model and dataset integration, and provides transparent, reproducible, and comparable results. By bridging capability-based evaluation and disciplinary diversity, SciEvalKit offers a standardized yet customizable infrastructure to benchmark the next generation of scientific foundation models and intelligent agents. The toolkit is open-sourced and actively maintained to foster community-driven development and progress in AI4Science.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of DiTs by compressing tokens into block-wise representation and selecting a small set of relevant key blocks, but still suffer from (i) quadratic selection cost on compressed tokens and (ii) increasing K required to maintain model quality as sequences grow. We identify that their inefficiency is due to the single-level design, as a single coarse level is insufficient to represent the global structure. In this paper, we introduce Log-linear Sparse Attention (LLSA), a trainable sparse attention mechanism for extremely long token sequences that reduces both selection and attention costs from quadratic to log-linear complexity by utilizing a hierarchical structure. LLSA performs hierarchical Top-K selection, progressively adopting sparse Top-K selection with the indices found at the previous level, and introduces a Hierarchical KV Enrichment mechanism that preserves global context while using fewer tokens of different granularity during attention computation. To support efficient training, we develop a high-performance GPU implementation that uses only sparse indices for both the forward and backward passes, eliminating the need for dense attention masks. We evaluate LLSA on high-resolution pixel-space image generation without using patchification and VAE encoding. LLSA accelerates attention inference by 28.27x and DiT training by 6.09x on 256x256 pixel token sequences, while maintaining generation quality. The results demonstrate that LLSA offers a promising direction for training long-sequence DiTs efficiently. Code is available at: https://github.com/SingleZombie/LLSA

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.

InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents

Information seeking is a fundamental requirement for humans. However, existing LLM agents rely heavily on open-web search, which exposes two fundamental weaknesses: online content is noisy and unreliable, and many real-world tasks require precise, domain-specific knowledge unavailable from the web. The emergence of the Model Context Protocol (MCP) now allows agents to interface with thousands of specialized tools, seemingly resolving this limitation. Yet it remains unclear whether agents can effectively leverage such tools -- and more importantly, whether they can integrate them with general-purpose search to solve complex tasks. Therefore, we introduce InfoMosaic-Bench, the first benchmark dedicated to multi-source information seeking in tool-augmented agents. Covering six representative domains (medicine, finance, maps, video, web, and multi-domain integration), InfoMosaic-Bench requires agents to combine general-purpose search with domain-specific tools. Tasks are synthesized with InfoMosaic-Flow, a scalable pipeline that grounds task conditions in verified tool outputs, enforces cross-source dependencies, and filters out shortcut cases solvable by trivial lookup. This design guarantees both reliability and non-triviality. Experiments with 14 state-of-the-art LLM agents reveal three findings: (i) web information alone is insufficient, with GPT-5 achieving only 38.2% accuracy and 67.5% pass rate; (ii) domain tools provide selective but inconsistent benefits, improving some domains while degrading others; and (iii) 22.4% of failures arise from incorrect tool usage or selection, highlighting that current LLMs still struggle with even basic tool handling.

Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction

While 3D Gaussian Splatting (3DGS) excels in static scene modeling, its extension to dynamic scenes introduces significant challenges. Existing dynamic 3DGS methods suffer from either over-smoothing due to low-rank decomposition or feature collision from high-dimensional grid sampling. This is because of the inherent spectral conflicts between preserving motion details and maintaining deformation consistency at different frequency. To address these challenges, we propose a novel dynamic 3DGS framework with hybrid explicit-implicit functions. Our approach contains three key innovations: a spectral-aware Laplacian encoding architecture which merges Hash encoding and Laplacian-based module for flexible frequency motion control, an enhanced Gaussian dynamics attribute that compensates for photometric distortions caused by geometric deformation, and an adaptive Gaussian split strategy guided by KDTree-based primitive control to efficiently query and optimize dynamic areas. Through extensive experiments, our method demonstrates state-of-the-art performance in reconstructing complex dynamic scenes, achieving better reconstruction fidelity.

RadFabric: Agentic AI System with Reasoning Capability for Radiology

Chest X ray (CXR) imaging remains a critical diagnostic tool for thoracic conditions, but current automated systems face limitations in pathology coverage, diagnostic accuracy, and integration of visual and textual reasoning. To address these gaps, we propose RadFabric, a multi agent, multimodal reasoning framework that unifies visual and textual analysis for comprehensive CXR interpretation. RadFabric is built on the Model Context Protocol (MCP), enabling modularity, interoperability, and scalability for seamless integration of new diagnostic agents. The system employs specialized CXR agents for pathology detection, an Anatomical Interpretation Agent to map visual findings to precise anatomical structures, and a Reasoning Agent powered by large multimodal reasoning models to synthesize visual, anatomical, and clinical data into transparent and evidence based diagnoses. RadFabric achieves significant performance improvements, with near-perfect detection of challenging pathologies like fractures (1.000 accuracy) and superior overall diagnostic accuracy (0.799) compared to traditional systems (0.229 to 0.527). By integrating cross modal feature alignment and preference-driven reasoning, RadFabric advances AI-driven radiology toward transparent, anatomically precise, and clinically actionable CXR analysis.

SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development

Large Language Models (LLMs) have shown strong capability in diverse software engineering tasks, e.g. code completion, bug fixing, and document generation. However, feature-driven development (FDD), a highly prevalent real-world task that involves developing new functionalities for large, existing codebases, remains underexplored. We therefore introduce SWE-Dev, the first large-scale dataset (with 14,000 training and 500 test samples) designed to evaluate and train autonomous coding systems on real-world feature development tasks. To ensure verifiable and diverse training, SWE-Dev uniquely provides all instances with a runnable environment and its developer-authored executable unit tests. This collection not only provides high-quality data for Supervised Fine-Tuning (SFT), but also enables Reinforcement Learning (RL) by delivering accurate reward signals from executable unit tests. Our extensive evaluations on SWE-Dev, covering 17 chatbot LLMs, 10 reasoning models, and 10 Multi-Agent Systems (MAS), reveal that FDD is a profoundly challenging frontier for current AI (e.g., Claude-3.7-Sonnet achieves only 22.45\% Pass@3 on the hard test split). Crucially, we demonstrate that SWE-Dev serves as an effective platform for model improvement: fine-tuning on training set enabled a 7B model comparable to GPT-4o on \textit{hard} split, underscoring the value of its high-quality training data. Code is available here \href{https://github.com/justLittleWhite/SWE-Dev}{https://github.com/justLittleWhite/SWE-Dev}.

IRNN: Innovation-driven Recurrent Neural Network for Time-Series Data Modeling and Prediction

Many real-world datasets are time series that are sequentially collected and contain rich temporal information. Thus, a common interest in practice is to capture dynamics of time series and predict their future evolutions. To this end, the recurrent neural network (RNN) has been a prevalent and effective machine learning option, which admits a nonlinear state-space model representation. Motivated by the resemblance between RNN and Kalman filter (KF) for linear state-space models, we propose in this paper Innovation-driven RNN (IRNN), a novel RNN architecture tailored to time-series data modeling and prediction tasks. By adapting the concept of "innovation" from KF to RNN, past prediction errors are adopted as additional input signals to update hidden states of RNN and boost prediction performance. Since innovation data depend on network parameters, existing training algorithms for RNN do not apply to IRNN straightforwardly. Thus, a tailored training algorithm dubbed input updating-based back-propagation through time (IU-BPTT) is further proposed, which alternates between updating innovations and optimizing network parameters via gradient descent. Experiments on real-world benchmark datasets show that the integration of innovations into various forms of RNN leads to remarkably improved prediction accuracy of IRNN without increasing the training cost substantially.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement

We demonstrate the ability of large language models (LLMs) to perform iterative self-improvement of robot policies. An important insight of this paper is that LLMs have a built-in ability to perform (stochastic) numerical optimization and that this property can be leveraged for explainable robot policy search. Based on this insight, we introduce the SAS Prompt (Summarize, Analyze, Synthesize) -- a single prompt that enables iterative learning and adaptation of robot behavior by combining the LLM's ability to retrieve, reason and optimize over previous robot traces in order to synthesize new, unseen behavior. Our approach can be regarded as an early example of a new family of explainable policy search methods that are entirely implemented within an LLM. We evaluate our approach both in simulation and on a real-robot table tennis task. Project website: sites.google.com/asu.edu/sas-llm/

EG-Gaussian: Epipolar Geometry and Graph Network Enhanced 3D Gaussian Splatting

In this paper, we explore an open research problem concerning the reconstruction of 3D scenes from images. Recent methods have adopt 3D Gaussian Splatting (3DGS) to produce 3D scenes due to its efficient training process. However, these methodologies may generate incomplete 3D scenes or blurred multiviews. This is because of (1) inaccurate 3DGS point initialization and (2) the tendency of 3DGS to flatten 3D Gaussians with the sparse-view input. To address these issues, we propose a novel framework EG-Gaussian, which utilizes epipolar geometry and graph networks for 3D scene reconstruction. Initially, we integrate epipolar geometry into the 3DGS initialization phase to enhance initial 3DGS point construction. Then, we specifically design a graph learning module to refine 3DGS spatial features, in which we incorporate both spatial coordinates and angular relationships among neighboring points. Experiments on indoor and outdoor benchmark datasets demonstrate that our approach significantly improves reconstruction accuracy compared to 3DGS-based methods.