arXiv subjects

Jinlin Wang

Publications and source records attributed to Jinlin Wang.

At least 19 recordsLinked to original sources

arXiv2026

FilmBench: A Film-Grade Benchmark for Cinematic Video Generation

Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score them with untrained, generic multimodal models. More fundamentally, their evaluation taxonomies remain rudimentary (overall visual quality, coarse text alignment and temporal smoothness) rather than the professional Cinematic Language criteria by which films are actually made and judged, so they assess basic video plausibility rather than film-grade craft. We introduce FilmBench, a text-to-video (T2V) and reference-to-video (R2V) benchmark grounded in the professional Cinematic Language of the film- academy tradition and co-developed with directors and faculty from the Beijing Film Academy and the Hujing Digital Media & Entertainment Group film studio. It rests on three choices. First, prompts are reverse-engineered from clips of award-winning films spanning 20 cinematic genres and chosen by professional directors, so every prompt is anchored to a verified live-action reference; the prompts follow real shot lists, and most script multiple shots (1,056 of the 1,169 prompts are multi-shot), unlike prior single-clip benchmarks. Second, evaluation follows a three-level Cinematic taxonomy of 3 axes, 12 components and 35 (T2V) +3 (R2V-only) sub-metrics. Third, we develop an in-house expert-grade automatic evaluation agent and open-source its core suite of Cinematic Language operators (FilmOps). Benchmarking leading video generation models (9 for T2V, 7 for R2V), the evaluator reproduces the human model ranking at model-level Spearman \r{ho} = 0.95 (T2V) and 0.96 (R2V). Scores fall well below prior web-style benchmarks, with two consistent gaps in dynamic aesthetics and a marked single- to multi-shot performance drop that widens for weaker models.

cs.CV↗

arXiv2026

Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation

Text-to-Image generation has evolved from basic image synthesis into a frequently used core capability in professional creative workflows, where simple text-image alignment can no longer satisfy users' pressing demands for faithful real-world reconstruction and genuine creative expression. Existing benchmarks, however, remain anchored in these foundational criteria and do not yet capture the nuanced capabilities that matter in authentic artistic practice, making it difficult to reliably distinguish state-of-the-art T2I models. To address the gap, we introduce Qwen-Image-Bench, a creator-centric benchmark co-designed with professional artists and grounded in real-world creation scenarios. Qwen-Image-Bench enriches conventional evaluation with two application-driven dimensions: Real-world Fidelity and Creative Generation. Drawing on the staged reasoning inherent in professional artistic workflows, we organize these five pillars into a top-down hierarchical taxonomy that further decomposes into 23 second-level sub-capabilities and 56 third-level verifiable rubrics. To ensure broad coverage, we curate 1000 stratified prompts with each prompt jointly exercising more than four fine-grained facets across multiple pillars. We train a unified judge model Q-Judger based on Qwen3.6-27B, supervised by 80 professional annotators from global art academies under blind labeling and triple-review protocols, that scores every image across all 56 verifiable facets, producing fine-grained, rubric-grounded, and fully attributable diagnostics rather than a single opaque score. Empirically, Qwen-Image-Bench reliably distinguishes leading T2I models, achieving the greatest separation on the two application-driven dimensions of Real-world Fidelity and Creative Generation where existing benchmarks provide little insight, while also providing a trustworthy optimization signal for production-level T2I development.

cs.CV↗

arXiv2026

Foundation Protocol: A Coordination Layer for Agentic Society

Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. As these systems scale, the bottleneck shifts away from raw model capability toward coordination. Agents need to form reliable relationships, organize multi-agent work, exchange value, support an AI economy, and stay safe and accountable under real-world oversight. This paper introduces the Foundation Protocol (FP), a graph-first coordination layer for an emerging human-AI society. FP unifies heterogeneous entities, including agents, tools, resources, humans, institutions, and organizations, and supports native multi-party organization and event-based collaboration. It also provides economic primitives for metering, receipts, and settlement, and treats policy, provenance, and audit as first-class concerns. FP is designed to wrap and bridge existing protocols rather than replace them, enabling incremental adoption while reducing integration and governance overhead. The aim is to keep autonomous agency composable while keeping accountability non-negotiable, so that coordination itself can become shared infrastructure for a human-AI society that is open, pluralistic, and governable.

cs.AI↗

arXiv2026

MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding

Medical visual grounding serves as a crucial foundation for fine-grained multimodal reasoning and interpretable clinical decision support. Despite recent advances in reinforcement learning (RL) for grounding tasks, existing approaches such as Group Relative Policy Optimization~(GRPO) suffer from severe reward sparsity when directly applied to medical images, primarily due to the inherent difficulty of localizing small or ambiguous regions of interest, which is further exacerbated by the rigid and suboptimal nature of fixed IoU-based reward schemes in RL. This leads to vanishing policy gradients and stagnated optimization, particularly during early training. To address this challenge, we propose MedLoc-R1, a performance-aware reward scheduling framework that progressively tightens the reward criterion in accordance with model readiness. MedLoc-R1 introduces a sliding-window performance tracker and a multi-condition update rule that automatically adjust the reward schedule from dense, easily obtainable signals to stricter, fine-grained localization requirements, while preserving the favorable properties of GRPO without introducing auxiliary networks or additional gradient paths. Experiments on three medical visual grounding benchmarks demonstrate that MedLoc-R1 consistently improves both localization accuracy and training stability over GRPO-based baselines. Our framework offers a general, lightweight, and effective solution for RL-based grounding in high-stakes medical applications. Code \& checkpoints are available at \hyperlink{}{https://github.com/MembrAI/MedLoc-R1}.

cs.CV↗

arXiv2025

AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning

Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents typically demonstrate improvements via self-evolving within a single domain, implicitly assuming a fixed environment distribution. Cross-environment learning has remained largely unmeasured: there is no standard collection of controllable, heterogeneous environments, nor a unified way to represent how agents learn. We address these gaps in two steps. First, we propose AutoEnv, an automated framework that treats environments as factorizable distributions over transitions, observations, and rewards, enabling low-cost (4.12 USD on average) generation of heterogeneous worlds. Using AutoEnv, we construct AutoEnv-36, a dataset of 36 environments with 358 validated levels, on which seven language models achieve 12-49% normalized reward, demonstrating the challenge of AutoEnv-36. Second, we formalize agent learning as a component-centric process driven by three stages of Selection, Optimization, and Evaluation applied to an improvable agent component. Using this formulation, we design eight learning methods and evaluate them on AutoEnv-36. Empirically, the gain of any single learning method quickly decrease as the number of environments increases, revealing that fixed learning methods do not scale across heterogeneous environments. Environment-adaptive selection of learning methods substantially improves performance but exhibits diminishing returns as the method space expands. These results highlight both the necessity and the current limitations of agent learning for scalable cross-environment generalization, and position AutoEnv and AutoEnv-36 as a testbed for studying cross-environment agent learning. The code is avaiable at https://github.com/FoundationAgents/AutoEnv.

cs.AI↗

arXiv2025

VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations

Visualization, a domain-specific yet widely used form of imagery, is an effective way to turn complex datasets into intuitive insights, and its value depends on whether data are faithfully represented, clearly communicated, and aesthetically designed. However, evaluating visualization quality is challenging: unlike natural images, it requires simultaneous judgment across data encoding accuracy, information expressiveness, and visual aesthetics. Although multimodal large language models (MLLMs) have shown promising performance in aesthetic assessment of natural images, no systematic benchmark exists for measuring their capabilities in evaluating visualizations. To address this, we propose VisJudge-Bench, the first comprehensive benchmark for evaluating MLLMs' performance in assessing visualization aesthetics and quality. It contains 3,090 expert-annotated samples from real-world scenarios, covering single visualizations, multiple visualizations, and dashboards across 32 chart types. Systematic testing on this benchmark reveals that even the most advanced MLLMs (such as GPT-5) still exhibit significant gaps compared to human experts in judgment, with a Mean Absolute Error (MAE) of 0.553 and a correlation with human ratings of only 0.428. To address this issue, we propose VisJudge, a model specifically designed for visualization aesthetics and quality assessment. Experimental results demonstrate that VisJudge significantly narrows the gap with human judgment, reducing the MAE to 0.421 (a 23.9% reduction) and increasing the consistency with human experts to 0.687 (a 60.5% improvement) compared to GPT-5. The benchmark is available at https://github.com/HKUSTDial/VisJudgeBench.

cs.CL↗

arXiv2025

Improving Context Fidelity via Native Retrieval-Augmented Reasoning

Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information. Existing approaches either rely on expensive supervised fine-tuning to generate evidence post-answer or train models to perform web searches without necessarily improving utilization of the given context. We propose CARE, a novel native retrieval-augmented reasoning framework that teaches LLMs to explicitly integrate in-context evidence within their reasoning process with the model's own retrieval capabilities. Our method requires limited labeled evidence data while significantly enhancing both retrieval accuracy and answer generation performance through strategically retrieved in-context tokens in the reasoning chain. Extensive experiments on multiple real-world and counterfactual QA benchmarks demonstrate that our approach substantially outperforms supervised fine-tuning, traditional retrieval-augmented generation methods, and external retrieval solutions. This work represents a fundamental advancement in making LLMs more accurate, reliable, and efficient for knowledge-intensive tasks.

cs.CL↗

arXiv2025

You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation

Large Language Models (LLMs) and code agents in software development are rapidly evolving from generating isolated code snippets to producing full-fledged software applications with graphical interfaces, interactive logic, and dynamic behaviors. However, current benchmarks fall short in evaluating such production-ready software, as they often rely on static checks or binary pass/fail scripts, failing to capture the interactive behaviors and runtime dynamics that define real-world usability - qualities that only emerge when an application is actively used. This is the blind spot of current evaluation: you don't know if an app works until you click through it, interact with it, and observe how it responds. To bridge this gap, we introduce RealDevWorld, a novel evaluation framework for automated end-to-end assessment of LLMs' ability to generate production-ready repositories from scratch. It features two key components: (1) RealDevBench, a diverse collection of 194 open-ended software engineering tasks across multiple domains, incorporating multimodal elements to reflect real-world complexity; and (2) AppEvalPilot, a new agent-as-a-judge evaluation system that simulates realistic, GUI-based user interactions to automatically and holistically assess software functional correctness, visual fidelity, and runtime behavior. The framework delivers fine-grained, task-specific diagnostic feedback, supporting nuanced evaluation beyond simple success/failure judgments. Empirical results show that RealDevWorld delivers effective, automatic, and human-aligned evaluations, achieving an accuracy of 0.92 and a correlation of 0.85 with expert human assessments, while significantly reducing the reliance on manual review. This enables scalable, human-aligned assessment of production-level software generated by LLMs. Our code is available on GitHub.

cs.SE↗

arXiv2025

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable of sophisticated reasoning, robust perception, and versatile action across diverse domains. As these agents increasingly drive AI research and practical applications, their design, evaluation, and continuous improvement present intricate, multifaceted challenges. This book provides a comprehensive overview, framing intelligent agents within modular, brain-inspired architectures that integrate principles from cognitive science, neuroscience, and computational research. We structure our exploration into four interconnected parts. First, we systematically investigate the modular foundation of intelligent agents, systematically mapping their cognitive, perceptual, and operational modules onto analogous human brain functionalities and elucidating core components such as memory, world modeling, reward processing, goal, and emotion. Second, we discuss self-enhancement and adaptive evolution mechanisms, exploring how agents autonomously refine their capabilities, adapt to dynamic environments, and achieve continual learning through automated optimization paradigms. Third, we examine multi-agent systems, investigating the collective intelligence emerging from agent interactions, cooperation, and societal structures. Finally, we address the critical imperative of building safe and beneficial AI systems, emphasizing intrinsic and extrinsic security threats, ethical alignment, robustness, and practical mitigation strategies necessary for trustworthy real-world deployment. By synthesizing modular AI architectures with insights from different disciplines, this survey identifies key research challenges and opportunities, encouraging innovations that harmonize technological advancement with meaningful societal benefit.

cs.AI↗

arXiv2025

AFlow: Automating Agentic Workflow Generation

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code is available at https://github.com/FoundationAgents/AFlow.

cs.AI↗

arXiv2024

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems. Our project can be found at https://github.com/geekan/MetaGPT

cs.AI↗

arXiv2024

FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval

Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, yet they struggle with tasks requiring the simultaneous retrieval of multiple facts, especially during generation. This paper identifies a novel "lost-in-the-middle" phenomenon, where LLMs progressively lose track of critical information throughout the generation process, resulting in incomplete or inaccurate retrieval. To address this challenge, we introduce Find All Crucial Texts (FACT), an iterative retrieval method that refines context through successive rounds of rewriting. This approach enables models to capture essential facts incrementally, which are often overlooked in single-pass retrieval. Experiments demonstrate that FACT substantially enhances multi-fact retrieval performance across various tasks, though improvements are less notable in general-purpose QA scenarios. Our findings shed light on the limitations of LLMs in multi-fact retrieval and underscore the need for more resilient long-context retrieval strategies.

cs.CL↗

arXiv2024

Data Interpreter: An LLM Agent For Data Science

Large Language Model (LLM)-based agents have shown effectiveness across many applications. However, their use in data science scenarios requiring solving long-term interconnected tasks, dynamic data adjustments and domain expertise remains challenging. Previous approaches primarily focus on individual tasks, making it difficult to assess the complete data science workflow. Moreover, they struggle to handle real-time changes in intermediate data and fail to adapt dynamically to evolving task dependencies inherent to data science problems. In this paper, we present Data Interpreter, an LLM-based agent designed to automatically solve various data science problems end-to-end. Our Data Interpreter incorporates two key modules: 1) Hierarchical Graph Modeling, which breaks down complex problems into manageable subproblems, enabling dynamic node generation and graph optimization; and 2) Programmable Node Generation, a technique that refines and verifies each subproblem to iteratively improve code generation results and robustness. Extensive experiments consistently demonstrate the superiority of Data Interpreter. On InfiAgent-DABench, it achieves a 25% performance boost, raising accuracy from 75.9% to 94.9%. For machine learning and open-ended tasks, it improves performance from 88% to 95%, and from 60% to 97%, respectively. Moreover, on the MATH dataset, Data Interpreter achieves remarkable performance with a 26% improvement compared to state-of-the-art baselines. The code is available at https://github.com/geekan/MetaGPT.

cs.AI↗

arXiv2024

Multi-interface engineering to realize all-solution processed highly efficient Kesterite solar cells

With the rapid development of Kesterite Cu2ZnSn(S, Se)4 solar cells in the past few years, how to achieve higher cost-performance ratio has become an important topic in the future development and industrialization of this technology. Herein, we demonstrate an all-solution route for the cell fabrication, in particular targeting at the solution processed window layer comprised of ZnO nanoparticles/Ag nanowires. A multi-interface engineering strategy assisted by organic polymers and molecules is explored to synergistically improve the film deposition, passivate the surface defects and facilitate the charge transfer. These efforts help us achieve high-performance and robust Kesterite solar cells at extremely low time and energy costs, with efficiency records of 14.37% and 13.12% being realized in rigid and flexible Kesterite solar cells, respectively. Our strategy here is also promising to be transplanted into other solar cells with similar geometric and energy band structures, helping reduce production costs and shorten the production cycle (i.e. increasing production capacity) of these photovoltaic industries.

cond-mat.mtrl-sci↗

arXiv2024

Vacancy enhanced cation ordering enables >15% efficiency in Kesterite solar cells

Atomic disorder, a widespread problem in compound crystalline materials, is a imperative affecting the performance of multi-chalcogenide Cu2ZnSn(S, Se)4 (CZTSSe) photovoltaic device known for its low cost and environmental friendliness. Cu-Zn disorder is particularly abundantly present in CZTSSe due to its extraordinarily low formation energy, having induced high-concentration deep defects and severe charge loss, while its regulation remains challenging due to the contradiction between disorder-order phase transition thermodynamics and atom-interchange kinetics. Herein, through introducing more vacancies in the CZTSSe surface, we explored a vacancy-assisted strategy to reduce the atom-interchange barrier limit to facilitate the Cu-Zn ordering kinetic process. The improvement in the Cu-Zn order degree has significantly reduced the charge loss in the device and helped us realize 15.4% (certified at 14.9%) and 13.5% efficiency (certified at 13.3%) in 0.27 cm2 and 1.1 cm2-area CZTSSe solar cells, respectively, thus bringing substantial advancement for emerging inorganic thin-film photovoltaics.

cond-mat.mtrl-sci↗

arXiv2024

Gradient bandgap enables >13% efficiency sulfide Kesterite solar cells with open-circuit voltage over 800 mV

Sulfide Kesterite Cu2ZnSnS4 (CZTS), a nontoxic and low-cost photovoltaic material, has always being facing severe charge recombination and poor carrier transport, resulting in the cell efficiency record stagnating around 11% for years. Gradient bandgap is a promising approach to relieve these issues, however, has not been effectively realized in Kesterite solar cells due to the challenges in controlling the gradient distribution of alloying elements at high temperatures. Herein, targeting at the Cd alloyed CZTS, we propose a pre-crystallization strategy to reduce the intense vertical mass transport and Cd rapid diffusion in the film growth process, thereby realizing front Cd-gradient CZTS absorber. The Cd-gradient CZTS absorber, exhibiting downward bending conduction band structure, has significantly enhanced the minority carrier transport and additionally improved band alignment and interface property of CZTS/CdS heterojunction. Ultimately, we have achieved a champion total-area efficiency of 13.5% (active-area efficiency: 14.1%) in the cell and in particular a high open-circuit voltage of >800 mV. We have also achieved a certified total-area cell efficiency of 13.16%, realizing a substantial step forward for the pure sulfide Kesterite solar cell.

cond-mat.mtrl-sci↗

arXiv2023

Defect Regulation by Palladium Incorporation towards Grain Boundaries of Kesterite solar cells

Kesterite Cu2ZnSn(S, Se)4 (CZTSSe) solar cell has emerged as one of the most promising candidates for thin-film photovoltaics. However, severe charge losses occurring at the grain boundaries (GBs) of Kesterite polycrystalline absorbers has hindered the improvement of cell performance. Herein, we report a redox reaction strategy involving palladium (Pd) to eliminate atomic vacancy defects such as VSn and VSe in GBs of the Kesterite absorbers. We demonstrate that PdSex compounds could form during the selenization process and distribute at the GBs and the absorber surfaces; thereby aid in the suppression of Sn and Se volatilization loss and inhibiting the formation of VSn and VSe defects. Furthermore, Pd(II)/Pd(IV) serves as a redox shuttle, i.e., on one hand, Pd(II) captures Se vapor from the reaction environment to produce PdSe2, on the other hand, PdSe2 provides Se atoms to the Kesterite absorber by being reduced to PdSe, thus contributing to the elimination of pre-existing VSe defects within GBs. These effects collectively reduce defects and enhance the p-type characteristics of the Kesterite absorber, leading to a significant reduction in charge recombination loss within the cell. As a result, high-performance Kesterite solar cells with a total-area efficiency of 14.5% have been achieved. This remarkable efficiency increase benefited from the redox reaction strategy offers a promising avenue for the precise regulation of defects in Kesterite solar cells and holds generally significant implications for the exploration of various other photovoltaic devices.

cond-mat.mtrl-sci↗

arXiv2023

Multinary Alloying Suppresses Defect Formation in Emerging Inorganic Solar Cells

The Cu2ZnSn(S, Se)4 (CZTSSe) emerging inorganic solar cell is highly promising for accelerating the large-scale and low-cost applications of thin-film photovoltaics. It possesses distinct advantages such as abundant and non-toxic constituent elements, high material stability, and excellent compatibility with industrial processes. However, CZTSSe solar cells still face challenges related to complex defects and charge losses. To overcome these limitations and improve the efficiency of CZTSSe solar cells, it is crucial to experimentally identify and mitigate deep defects. In this study, we reveal that the dominant deep defect in CZTSSe materials exhibits donor characteristics. We propose that incomplete cation exchange during the multi-step crystallization reactions of CZTSSe is the kinetics mechanism responsible for the defect formation. To address this issue, we introduce an elemental synergistic alloying approach aimed at weakening the metal-chalcogen bond strength and the stability of intermediate phases. This alloying strategy has facilitated the kinetics of cation exchange, leading to a significant reduction in charge losses within the CZTSSe absorber. As a result, we have achieved a cell efficiency of over 14.5%. These results represent a significant advancement for emerging inorganic solar cells and additionally bring more opportunities for the precise identification and regulation of defects in a wider range of multinary inorganic compounds.

cond-mat.mtrl-sci↗