arXiv subjects

Lei Bai

Publications and source records attributed to Lei Bai.

At least 109 records · Page 6Linked to original sources

arXiv2026

Benchmarking AI-based data assimilation to advance data-driven global weather forecasting

Research on Artificial Intelligence (AI)-based Data Assimilation (DA) is expanding rapidly. However, the absence of an objective, comprehensive, and real-world benchmark hinders the fair comparison of diverse methods. Here, we introduce DABench, a benchmark designed for contributing to the development and evaluation of AI-based DA methods. By integrating real-world observations, DABench provides an objective and fair platform for validating long-term closed-loop DA cycles, supporting both deterministic and ensemble configurations. Furthermore, we assess the efficacy of AI-based DA in generating initial conditions for the advanced AI-based weather forecasting model to produce accurate medium-range global weather forecasting. Our dual-validation, utilizing both reanalysis data and independent radiosonde observations, demonstrates that AI-based DA achieves performance competitive with state-of-the-art AI-driven four-dimensional variational frameworks across both global weather DA and medium-range forecasting metrics. We invite the research community to utilize DABench to accelerate the advancement of AI-based DA for global weather forecasting.

cs.LG↗

arXiv2026

PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level

Physics problem-solving is a challenging domain for AI models, requiring integration of conceptual understanding, mathematical reasoning, and interpretation of physical diagrams. Existing evaluations fail to capture the full breadth and complexity of undergraduate physics, whereas this level provides a rigorous yet standardized testbed for pedagogical assessment of multi-step physical reasoning. To this end, we present PhysUniBench, a large-scale multimodal benchmark designed to evaluate and improve the reasoning capabilities of multimodal large language models (MLLMs) specifically on undergraduate-level physics problems. PhysUniBench consists of 3,304 physics questions spanning 8 major sub-disciplines of physics, each accompanied by one visual diagram. The benchmark includes both open-ended and multiple-choice questions, systematically curated and difficulty-rated through an iterative process. The benchmark's construction involved a rigorous multi-stage process, including multiple roll-outs, expert-level evaluation, automated filtering of easily solved problems, and a nuanced difficulty grading system with five levels. Through extensive experiments, we observe that current models encounter substantial challenges in physics reasoning, where GPT-5 achieves only 51.6% accuracy in the PhysUniBench. These results highlight that current MLLMs struggle with advanced physics reasoning, especially on multi-step problems and those requiring precise diagram interpretation. By providing a broad and rigorous assessment tool, PhysUniBench aims to drive progress in AI for Science, encouraging the development of models with stronger physical reasoning, problem-solving skills, and multimodal understanding.

cs.AI↗

arXiv2026

Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale

Large Language Models (LLMs) have rapidly advanced, with Gemini-3-Pro setting a new performance milestone. In this work, we explore collective intelligence as an alternative to monolithic scaling, and demonstrate that open-source LLMs' collaboration can surpass Gemini-3-Pro. We first revisit LLM routing and aggregation at scale and identify three key bottlenecks: (1) current train-free routers are limited by a query-based paradigm focusing solely on textual similarity; (2) recent aggregation methods remain largely static, failing to select appropriate aggregators for different tasks;(3) the complementarity of routing and aggregation remains underutilized. To address these problems, we introduce JiSi, a novel framework designed to release the full potential of LLMs' collaboration through three innovations: (1) Query-Response Mixed Routing capturing both semantic information and problem difficulty; (2) Support-Set-based Aggregator Selection jointly evaluating the aggregation and domain capacity of aggregators; (3) Adaptive Routing-Aggregation Switch dynamically leveraging the advantages of routing and aggregation. Comprehensive experiments on nine benchmarks demonstrate that JiSi can surpass Gemini-3-Pro with only 47% costs by orchestrating ten open-source LLMs, while outperforming mainstream baselines. It suggests that collective intelligence represents a novel path towards Artificial General Intelligence (AGI).

cs.AI↗

arXiv2026

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

The transition from symbolic manipulation to science-grade reasoning represents a pivotal frontier for Large Language Models (LLMs), with physics serving as the critical test anchor for binding abstract logic to physical reality. Physics demands that a model maintain physical consistency with the laws governing the universe, a task that fundamentally requires multimodal perception to ground abstract logic in reality. At the Olympiad level, diagrams are often constitutive rather than illustrative, containing essential constraints, such as boundary conditions and spatial symmetries, that are absent from the text. To bridge this visual-logical gap, we introduce P1-VL, a family of open-source vision-language models engineered for advanced scientific reasoning. Our method harmonizes Curriculum Reinforcement Learning, which employs progressive difficulty expansion to stabilize post-training, with Agentic Augmentation, enabling iterative self-verification at inference. Evaluated on HiPhO, a rigorous benchmark of 13 exams from 2024-2025, our flagship P1-VL-235B-A22B becomes the first open-source Vision-Language Model (VLM) to secure 12 gold medals and achieves the state-of-the-art performance in the open-source models. Our agent-augmented system achieves the No.2 overall rank globally, trailing only Gemini-3-Pro. Beyond physics, P1-VL demonstrates remarkable scientific reasoning capacity and generalizability, establishing significant leads over base models in STEM benchmarks. By open-sourcing P1-VL, we provide a foundational step toward general-purpose physical intelligence to better align visual perceptions with abstract physical laws for machine scientific discovery.

cs.AI↗

arXiv2026

ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems

Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast, this work attempts to study using LLM-based agents to design collaborative AI systems autonomously. To explore this problem, we first introduce ComfyBench to evaluate agents's ability to design collaborative AI systems in ComfyUI. ComfyBench is a comprehensive benchmark comprising 200 diverse tasks covering various instruction-following generation challenges, along with detailed annotations for 3,205 nodes and 20 workflows. Based on ComfyBench, we further develop ComfyAgent, a novel framework that empowers LLM-based agents to autonomously design collaborative AI systems by generating workflows. ComfyAgent is based on two core concepts. First, it represents workflows with code, which can be reversibly converted into workflows and executed as collaborative systems by the interpreter. Second, it constructs a multi-agent system that cooperates to learn from existing workflows and generate new workflows for a given task. While experimental results demonstrate that ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15\% of creative tasks. LLM-based agents still have a long way to go in autonomously designing collaborative AI systems. Progress with ComfyBench is paving the way for more intelligent and autonomous collaborative AI systems.

cs.CL↗

arXiv2026

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining. Recent research has witnessed a transition from reinforcement learning (RL)-free to RL-based methods. Current RL-based methods either rely on dense external reward signals or extract intrinsic reward signals from LLMs themselves. However, these approaches diverge from the self-evolution mechanisms observed in human intelligence, where individuals learn and improve through mutual discussion and collaboration. In this work, we introduce Co-Evolving Multi-Agent Systems (CoMAS), a novel framework that enables agents to improve autonomously by learning from inter-agent interactions without external supervision. CoMAS generates intrinsic rewards from rich discussion dynamics, employs an LLM-as-a-judge mechanism to formulate these rewards, and optimizes each agent's policy through RL, thereby enabling decentralized and scalable co-evolution. Experimental results demonstrate that CoMAS consistently outperforms untrained agents and achieves state-of-the-art performance across most evaluation settings. Ablation studies confirm the necessity of interaction-based reward signals and reveal promising scalability as the number and diversity of agents increase. These findings establish CoMAS as a novel and effective paradigm for self-evolution in LLM-based agents.

cs.CL↗

arXiv2026

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for generation, verification, and evolution. These subsystems are supported by foundational capabilities for deep research, solution optimization, and long horizon memory. The architecture allows InternAgent-1.5 to operate continuously across extended discovery cycles while maintaining coherent and improving behavior. It also enables the system to coordinate computational modeling and laboratory experimentation within a single unified system. We evaluate InternAgent-1.5 on scientific reasoning benchmarks such as GAIA, HLE, GPQA, and FrontierScience, and the system achieves leading performance that demonstrates strong foundational capabilities. Beyond these benchmarks, we further assess two categories of discovery tasks. In algorithm discovery tasks, InternAgent-1.5 autonomously designs competitive methods for core machine learning problems. In empirical discovery tasks, it executes complete computational or wet lab experiments and produces scientific findings in earth, life, biological, and physical domains. Overall, these results show that InternAgent-1.5 provides a general and scalable framework for autonomous scientific discovery.

cs.AI↗

arXiv2026

SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery

The current landscape of AI for Science (AI4S) is predominantly anchored in large-scale textual corpora, where generative AI systems excel at hypothesis generation, literature search, and multi-modal reasoning. However, a critical bottleneck for accelerating closed-loop scientific discovery remains the utilization of raw experimental data. Characterized by extreme heterogeneity, high specificity, and deep domain expertise requirements, raw data possess neither direct semantic alignment with linguistic representations nor structural homogeneity suitable for a unified embedding space. The disconnect prevents the emerging class of Artificial General Intelligence for Science (AGI4S) from effectively interfacing with the physical reality of experimentation. In this work, we extend the text-centric AI-Ready concept to Scientific AI-Ready data paradigm, explicitly formalizing how scientific data is specified, structured, and composed within a computational workflow. To operationalize this idea, we propose SciDataCopilot, an autonomous agentic framework designed to handle data ingestion, scientific intent parsing, and multi-modal integration in a end-to-end manner. By positioning data readiness as a core operational primitive, the framework provides a principled foundation for reusable, transferable systems, enabling the transition toward experiment-driven scientific general intelligence. Extensive evaluations across three heterogeneous scientific domains show that SciDataCopilot improves efficiency, scalability, and consistency over manual pipelines, with up to 30$\times$ speedup in data preparation.

cs.DB↗

arXiv2026

XiChen: A global weather observation-to-forecast machine learning system via four-dimensional variational gradient-guided flexible assimilation

Machine Learning (ML) has shown great promise in revolutionizing weather forecasting, yet most ML systems still rely on initial conditions generated by Numerical Weather Prediction (NWP) systems. End-to-end ML models aim to eliminate this dependency, but they often rely on observation-specific encoders and require redesign or retraining when observation sources change, thereby limiting their operational robustness. Here, we introduce XiChen, a global weather observation-to-forecast ML system via four-dimensional variational (4DVar) gradient-guided flexible assimilation. We demonstrate that the gradient of the 4DVar cost function serves as a physically grounded interface that maps heterogeneous observations into a common state space. This novel formulation enables XiChen to flexibly assimilate diverse conventional and raw satellite observations while preserving physical consistency. Experiments show that the system achieves forecasting metrics competitive with operational NWP systems. This work provides a practical and physically consistent route toward operational ML-based global weather forecasting systems with heterogeneous and evolving observations.

cs.LG↗

arXiv2026

MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation

While the complex reasoning capability of Large Language Models (LLMs) has attracted significant attention, single-agent systems often encounter inherent performance ceilings in complex tasks such as code generation. Multi-agent collaboration offers a promising avenue to transcend these boundaries. However, existing frameworks typically rely on prompt-based test-time interactions or multi-role configurations trained with homogeneous parameters, limiting error correction capabilities and strategic diversity. In this paper, we propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2), which integrates policy learning with multi-agent tree search by formulating the multi-agent collaborative exploration process as a dynamic and learnable environment. By allowing agents to iteratively explore and refine within the environment, the framework facilitates evolution from parameter-sharing homogeneous multi-role training to heterogeneous multi-agent training, breaking through single-agent capability limits. We also introduce an efficient inference strategy MARTI-MARS2-T+ to fully exploit the scaling potential of multi-agent collaboration at test time. We conduct extensive experiments across varied model scales (8B, 14B, and 32B) on challenging code generation benchmarks. Utilizing two collaborating 32B models, MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1. Furthermore, MARTI-MARS2 reveals a novel scaling law: shifting from single-agent to homogeneous multi-role and ultimately to heterogeneous multi-agent paradigms progressively yields higher RL performance ceilings, robust TTS capabilities, and greater policy diversity, suggesting that policy diversity is critical for scaling intelligence via multi-agent reinforcement learning.

cs.LG↗

arXiv2026

IceBench-S2S: A Benchmark of Deep Learning for Challenging Subseasonal-to-Seasonal Daily Arctic Sea Ice Forecasting in Deep Latent Space

Arctic sea ice plays a critical role in regulating Earth's climate system, significantly influencing polar ecological stability and human activities in coastal regions. Recent advances in artificial intelligence have facilitated the development of skillful pan-Arctic sea ice forecasting systems, where data-driven approaches showcase tremendous potential to outperform conventional physics-based numerical models in terms of accuracy, computational efficiency and forecasting lead times. Despite the latest progress made by deep learning (DL) forecasting models, most of their skillful forecasting lead times are confined to daily subseasonal scale and monthly averaged values for up to six months, which drastically hinders their deployment for real-world applications, e.g., maritime routine planning for Arctic transportation and scientific investigation. Extending daily forecasts from subseasonal to seasonal (S2S) scale is scientifically crucial for operational applications. To bridge the gap between the forecasting lead time of current DL models and the significant daily S2S scale, we introduce IceBench-S2S, the first comprehensive benchmark for evaluating DL approaches in mitigating the challenge of forecasting Arctic sea ice concentration in successive 180-day periods. It proposes a generalized framework that first compresses spatial features of daily sea ice data into a deep latent space. The temporally concatenated deep features are subsequently modeled by DL-based forecasting backbones to predict the sea ice variation at S2S scale. IceBench-S2S provides a unified training and evaluation pipeline for different backbones, along with practical guidance for model selection in polar environmental monitoring tasks.

cs.LG↗

arXiv2026

A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation

Low-Rank Adaptation (LoRA) is a fundamental parameter-efficient fine-tuning method that balances efficiency and performance in large-scale neural networks. However, the proliferation of LoRA variants has led to fragmentation in methodology, theory, code, and evaluation. To this end, this work presents the first unified study of LoRA variants, offering a systematic taxonomy, unified theoretical review, structured codebase, and standardized empirical assessment. First, we categorize LoRA variants along four principal axes: rank, optimization dynamics, initialization, and integration with Mixture-of-Experts. Then, we review their relationships and evolution within a common theoretical framework focused on low-rank update dynamics. Further, we introduce LoRAFactory, a modular codebase that implements variants through a unified interface, supporting plug-and-play experimentation and fine-grained analysis. Last, using this codebase, we conduct a large-scale evaluation across natural language generation, natural language understanding, and image classification tasks, systematically exploring key hyperparameters. Our results uncover several findings, notably: LoRA and its variants exhibit pronounced sensitivity to the choices of learning rate compared to other hyperparameters; moreover, with proper hyperparameter configurations, LoRA consistently matches or surpasses the performance of most of its variants.

cs.LG↗

arXiv2026

Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism

The foundation of reproducible science lies in protocols that are precise, logically ordered, and executable. The autonomous generation of these protocols through natural language queries could greatly improve the efficiency of the reproduction process. However, current leading large language models (LLMs) often generate incomplete or inconsistent protocols, limiting their utility. To address this limitation, we first introduce SciRecipe, a large-scale dataset of over 12K structured protocols spanning 27 biological subfields and encompassing both comprehension and problem-solving tasks. To further improve protocol generation, we propose the "Sketch-and-Fill" paradigm, which separates analysis, structuring, and expression to ensure each step is explicit and verifiable. Complementing this, the structured component-based reward mechanism evaluates step granularity, action order, and semantic fidelity, aligning model optimization with experimental reliability. Building on these components, we develop Thoth, trained through a staged Knowledge-to-Action process that progresses from knowledge acquisition to operational reasoning and ultimately to robust, executable protocol generation. Across multiple benchmarks, Thoth consistently surpasses both proprietary and open-source LLMs, achieving significant improvements in step alignment, logical sequencing, and semantic accuracy. Our approach paves the way for reliable scientific assistants that bridge knowledge with experimental execution. All data, code, and models will be released publicly.

cs.AI↗

arXiv2026

Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge

Recent advancements in multimodal large language models and vision-languageaction models have significantly driven progress in Embodied AI. As the field transitions toward more complex task scenarios, multi-agent system frameworks are becoming essential for achieving scalable, efficient, and collaborative solutions. This shift is fueled by three primary factors: increasing agent capabilities, enhancing system efficiency through task delegation, and enabling advanced human-agent interactions. To address the challenges posed by multi-agent collaboration, we propose the Multi-Agent Robotic System (MARS) Challenge, held at the NeurIPS 2025 Workshop on SpaVLE. The competition focuses on two critical areas: planning and control, where participants explore multi-agent embodied planning using vision-language models (VLMs) to coordinate tasks and policy execution to perform robotic manipulation in dynamic environments. By evaluating solutions submitted by participants, the challenge provides valuable insights into the design and coordination of embodied multi-agent systems, contributing to the future development of advanced collaborative AI systems.

cs.RO↗

arXiv2026

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation, featuring three structured levels: agent activation, task planning, and trajectory perception. VIKI-Bench includes diverse robot embodiments, multi-view visual observations, and structured supervision signals to evaluate reasoning grounded in visual inputs. To demonstrate the utility of VIKI-Bench, we propose VIKI-R, a two-stage framework that fine-tunes a pretrained vision-language model (VLM) using Chain-of-Thought annotated demonstrations, followed by reinforcement learning under multi-level reward signals. Our extensive experiments show that VIKI-R significantly outperforms baselines method across all task levels. Furthermore, we show that reinforcement learning enables the emergence of compositional cooperation patterns among heterogeneous agents. Together, VIKI-Bench and VIKI-R offer a unified testbed and method for advancing multi-agent, visual-driven cooperation in embodied AI systems.

cs.AI↗

arXiv2026

Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System

Meta-analysis is a systematic research methodology that synthesizes data from multiple existing studies to derive comprehensive conclusions. This approach not only mitigates limitations inherent in individual studies but also facilitates novel discoveries through integrated data analysis. Traditional meta-analysis involves a complex multi-stage pipeline including literature retrieval, paper screening, and data extraction, which demands substantial human effort and time. However, while LLM-based methods can accelerate certain stages, they still face significant challenges, such as hallucinations in paper screening and data extraction. In this paper, we propose a multi-agent system, Manalyzer, which achieves end-to-end automated meta-analysis through tool calls. The hybrid review, hierarchical extraction, self-proving, and feedback checking strategies implemented in Manalyzer significantly alleviate these two hallucinations. To comprehensively evaluate the performance of meta-analysis, we construct a new benchmark comprising 729 papers across 3 domains, encompassing text, image, and table modalities, with over 10,000 data points. Extensive experiments demonstrate that Manalyzer achieves significant performance improvements over the LLM baseline in multi meta-analysis tasks. Project page: https://black-yt.github.io/meta-analysis-page/ .

cs.AI↗

arXiv2026

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration

Advances in single-cell sequencing have enabled high-resolution profiling of diverse molecular modalities, while integrating unpaired multi-omics single-cell data remains challenging. Existing approaches either rely on pair information or prior correspondences, or require computing a global pairwise coupling matrix, limiting their scalability and flexibility. In this paper, we introduce a scalable and flexible generative framework called single-cell Multi-omics Regularized Disentangled Representations (scMRDR) for unpaired multi-omics integration. Specifically, we disentangle each cell's latent representations into modality-shared and modality-specific components using a well-designed $β$-VAE architecture, which are augmented with isometric regularization to preserve intra-omics biological heterogeneity, adversarial objective to encourage cross-modal alignment, and masked reconstruction loss strategy to address the issue of missing features across modalities. Our method achieves excellent performance on benchmark datasets in terms of batch correction, modality alignment, and biological signal preservation. Crucially, it scales effectively to large-scale datasets and supports integration of more than two omics, offering a powerful and flexible solution for large-scale multi-omics data integration and downstream biological discovery.

q-bio.QM↗

arXiv2026

LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing

Large language model (LLM) routing assigns each query to the most suitable model from an ensemble. We introduce LLMRouterBench, a large-scale benchmark and unified framework for LLM routing. It comprises over 400K instances from 21 datasets and 33 models. Moreover, it provides comprehensive metrics for both performance-oriented routing and performance-cost trade-off routing, and integrates 10 representative routing baselines. Using LLMRouterBench, we systematically re-evaluate the field. While confirming strong model complementarity-the central premise of LLM routing-we find that many routing methods exhibit similar performance under unified evaluation, and several recent approaches, including commercial routers, fail to reliably outperform a simple baseline. Meanwhile, a substantial gap remains to the Oracle, driven primarily by persistent model-recall failures. We further show that backbone embedding models have limited impact, that larger ensembles exhibit diminishing returns compared to careful model curation, and that the benchmark also enables latency-aware analysis. All code and data are available at https://github.com/ynulihao/LLMRouterBench.

cs.AI↗