Zichen Chen

Zhangchen Xu, Junda Chen, Yue Huang et al.

Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts. Yet existing benchmarks for frontier models primarily evaluate either single-turn responses or short-horizon agent trajectories, failing to capture the challenges of sustained iterative improvement over extended time horizons. To address this gap, we introduce AutoLab, a new benchmark for ultra long-horizon closed-loop optimization. AutoLab consists of 36 realistic, expert-curated tasks spanning four diverse domains: system optimization, puzzle & challenge, model development, and CUDA kernel optimization. Each task begins with a correct but deliberately suboptimal baseline and challenges agents to improve it within a strict wall-clock budget. Evaluating 17 state-of-the-art models reveals the dominant predictor of success is not the quality of an agent's initial attempt, but its persistence in repeatedly benchmarking, editing, and incorporating empirical feedback. While claude-opus-4.6 exhibits strong long-horizon optimization capabilities, most frontier models, including several proprietary ones, either terminate prematurely or exhaust their budgets with minimal progress. These results underscore the importance of time awareness and persistent iteration in autonomous agents. We open-source the full benchmark, evaluation harness, and task artifacts, to accelerate research toward truly capable long-horizon agents.

Yuanyuan Chen, Zichen Chen, Pengcheng Wu et al.

Large-scale neural networks possess considerable expressive power. They are well-suited for complex learning tasks in industrial applications. However, large-scale models pose significant challenges for training under the current Federated Learning (FL) paradigm. Existing approaches for efficient FL training often leverage model parameter dropout. However, manipulating individual model parameters is not only inefficient in meaningfully reducing the communication overhead when training large-scale FL models, but may also be detrimental to the scaling efforts and model performance as shown by recent research. To address these issues, we propose the Federated Opportunistic Block Dropout (FedOBD) approach. The key novelty is that it decomposes large-scale models into semantic blocks so that FL participants can opportunistically upload quantized blocks, which are deemed to be significant towards training the model, to the FL server for aggregation. Extensive experiments evaluating FedOBD against four state-of-the-art approaches based on multiple real-world datasets show that it reduces the overall communication overhead by more than 88% compared to the best performing baseline approach, while achieving the highest test accuracy. To the best of our knowledge, FedOBD is the first approach to perform dropout on FL models at the block level rather than at the individual parameter level.

Bowen Jiang, Yuan Yuan, Maohao Shen et al. · uw

Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simulates 1,000 realistic user-chatbot interactions on 300+ scenarios, 20,000+ user preferences, and 128k-token context windows, where most user preferences are implicitly revealed to reflect real-world interactions. Using this data, we investigate how reinforcement fine-tuning enables a model to improve its long-context reasoning capabilities for user understanding and personalization. We also develop a framework for training an agentic memory system, which maintains a single, human-readable memory that grows with each user over time. In our experiments, frontier LLMs still struggle with implicit personalization, achieving only 37-48% accuracy. While they support long context windows, reasoning remains the bottleneck for implicit personalization tasks. Using reinforcement fine-tuning, we successfully train Qwen3-4B to outperforms GPT-5, reaching 53% accuracy in implicit personalization. Moreover, our agentic memory framework achieves state-of-the-art 55% accuracy while using 16x fewer input tokens, relying on a 2k-token memory instead of full 32k conversation histories. These results underscore the impact of our dataset and demonstrate agentic memory as a scalable path toward real-world personalized intelligence.

Yuanyuan Chen, Zichen Chen, Sheng Guo et al.

Artificial intelligence (AI)-empowered industrial fault diagnostics is important in ensuring the safe operation of industrial applications. Since complex industrial systems often involve multiple industrial plants (possibly belonging to different companies or subsidiaries) with sensitive data collected and stored in a distributed manner, collaborative fault diagnostic model training often needs to leverage federated learning (FL). As the scale of the industrial fault diagnostic models are often large and communication channels in such systems are often not exclusively used for FL model training, existing deployed FL model training frameworks cannot train such models efficiently across multiple institutions. In this paper, we report our experience developing and deploying the Federated Opportunistic Block Dropout (FEDOBD) approach for industrial fault diagnostic model training. By decomposing large-scale models into semantic blocks and enabling FL participants to opportunistically upload selected important blocks in a quantized manner, it significantly reduces the communication overhead while maintaining model performance. Since its deployment in ENN Group in February 2022, FEDOBD has served two coal chemical plants across two cities in China to build industrial fault prediction models. It helped the company reduce the training communication overhead by over 70% compared to its previous AI Engine, while maintaining model performance at over 85% test F1 score. To our knowledge, it is the first successfully deployed dropout-based FL approach.

Yuetai Li, Yichen Feng, Zhangchen Xu et al.

Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluates AI agents on the workflows that experts identify as high-priority for delegation, empowering humans based on their needs instead of replacing them with GDP value. JobBench covers 130 agentic tasks across 35 occupations. Each task is packaged as a workspace of heterogeneous reference files, requiring the agent to reason through the cluttered information streams of real professional work. Outputs are graded by a fact-anchored chain of rubrics, averaging 35.6 binary criteria per task. We evaluate 36 models; the strongest, Claude Opus~4.7 under Claude Code, reaches only 45.9 %. We hope JobBench shifts the community's target labour-market effect from replacement to enhancement: building agents that do what humans actually want delegated, not only what is most economically valuable.

Zichen Chen, Jianda Chen, Ambuj Singh et al.

Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. We address this by introducing XplainLLM, a dataset accompanying an explanation framework designed to enhance LLM transparency and reliability. Our dataset comprises 24,204 instances where each instance interprets the LLM's reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoder-only Llama-3 and the encoder-only RoBERTa. XplainLLM also features a framework for generating grounded explanations and the debugger-scores for multidimensional quality analysis. Our explanations include why-choose and why-not-choose components, reason-elements, and debugger-scores that collectively illuminate the LLM's reasoning behavior. Our evaluations demonstrate XplainLLM's potential to reduce hallucinations and improve grounded explanation generation in LLMs. XplainLLM is a resource for researchers and practitioners to build trust and verify the reliability of LLM outputs.

Yue Huang, Yu Jiang, Wenjie Wang et al.

Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems promise unprecedented scalability and autonomy, their collective interaction also gives rise to failure modes that cannot be reduced to individual agents. Understanding these emergent risks is therefore critical. Here, we present a pioneer study of such emergent multi-agent risk in workflows that involve competition over shared resources (e.g., computing resources or market share), sequential handoff collaboration (where downstream agents see only predecessor outputs), collective decision aggregation, and others. Across these settings, we observe that such group behaviors arise frequently across repeated trials and a wide range of interaction conditions, rather than as rare or pathological cases. In particular, phenomena such as collusion-like coordination and conformity emerge with non-trivial frequency under realistic resource constraints, communication protocols, and role assignments, mirroring well-known pathologies in human societies despite no explicit instruction. Moreover, these risks cannot be prevented by existing agent-level safeguards alone. These findings expose the dark side of intelligent multi-agent systems: a social intelligence risk where agent collectives, despite no instruction to do so, spontaneously reproduce familiar failure patterns from human societies.

Zichen Chen, Jianda Chen, Yuanyuan Chen et al.

Language models (LMs) like GPT-4 are important in AI applications, but their opaque decision-making process reduces user trust, especially in safety-critical areas. We introduce LMExplainer, a novel knowledge-grounded explainer that clarifies the reasoning process of LMs through intuitive, human-understandable explanations. By leveraging a graph attention network (GAT) with a large-scale knowledge graph (KG), LMExplainer not only precisely narrows the reasoning space to focus on the most relevant knowledge but also grounds its reasoning in structured, verifiable knowledge to reduce hallucinations and enhance interpretability. LMExplainer effectively generates human-understandable explanations to enhance transparency and streamline the decision-making process. Additionally, by incorporating debugging into the explanation, it offers expertise suggestions that improve LMs from a developmental perspective. Thus, LMExplainer stands as an enhancement in making LMs more accessible and understandable to users. We evaluate LMExplainer on benchmark datasets such as CommonsenseQA and OpenBookQA, demonstrating that it outperforms most existing methods. By comparing the explanations generated by LMExplainer with those of other models, we show that our approach offers more comprehensive and clearer explanations of the reasoning process. LMExplainer provides a deeper understanding of the inner workings of LMs, advancing towards more reliable, transparent, and equitable AI.

Jianda Chen, Wen Zheng Terence Ng, Zichen Chen et al.

In reinforcement learning with image-based inputs, it is crucial to establish a robust and generalizable state representation. Recent advancements in metric learning, such as deep bisimulation metric approaches, have shown promising results in learning structured low-dimensional representation space from pixel observations, where the distance between states is measured based on task-relevant features. However, these approaches face challenges in demanding generalization tasks and scenarios with non-informative rewards. This is because they fail to capture sufficient long-term information in the learned representations. To address these challenges, we propose a novel State Chrono Representation (SCR) approach. SCR augments state metric-based representations by incorporating extensive temporal information into the update step of bisimulation metric learning. It learns state distances within a temporal framework that considers both future dynamics and cumulative rewards over current and long-term future states. Our learning strategy effectively incorporates future behavioral information into the representation space without introducing a significant number of additional parameters for modeling dynamics. Extensive experiments conducted in DeepMind Control and Meta-World environments demonstrate that SCR achieves better performance comparing to other recent metric-based methods in demanding generalization tasks. The codes of SCR are available in https://github.com/jianda-chen/SCR.

Yichen Feng, Yuetai Li, Chunjiang Liu et al.

Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an explicit aesthetic judgment. Most existing solutions reduce this judgment to predicting a scalar score for a single image. We first ask whether such scores faithfully capture comparative preference: in a controlled study with eight expert annotators, score-derived rankings align poorly with the same annotators' direct comparisons, while direct ranking yields substantially higher inter-annotator agreement on best- and worst-image labels. Motivated by this finding, we introduce the Visual Aesthetic Benchmark (VAB), which casts aesthetic evaluation as comparative selection over candidate sets with matched subject matter. VAB contains 400 tasks and 1,195 images across fine art, photography, and illustration, with labels derived from the consensus of 10 independent expert judges per task. Evaluating 20 frontier MLLMs and six dedicated visual-quality reward models, we find that the strongest system identifies both the best and the worst image correctly across three random permutations of the candidate order in only 26.5% of tasks, far below the 68.9% achieved by human experts. Fine-tuning a 35B-parameter model on 2,000 expert examples brings its accuracy close to that of a 397B-parameter open-weight model, suggesting that the comparative signal in VAB is transferable. Together, these results expose a clear and measurable gap between current multimodal models and expert aesthetic judgment, and VAB provides the first set-based, expert-grounded testbed on which that gap can be tracked and closed.

Qiming Wu, Zichen Chen, Will Corcoran et al.

Large language models (LLMs) have achieved remarkable success in natural language processing (NLP), demonstrating significant capabilities in processing and understanding text data. However, recent studies have identified limitations in LLMs' ability to manipulate, program, and reason about structured data, especially graphs. We introduce GraphEval36K, the first comprehensive graph dataset, comprising 40 graph coding problems and 36,900 test cases to evaluate the ability of LLMs on graph problem-solving. Our dataset is categorized into eight primary and four sub-categories to ensure a thorough evaluation across different types of graphs. We benchmark ten LLMs, finding that private models outperform open-source ones, though the gap is narrowing. We also analyze the performance of LLMs across directed vs undirected graphs, different kinds of graph concepts, and network models. Furthermore, to improve the usability of our evaluation framework, we propose Structured Symbolic Decomposition (SSD), an instruction-based method designed to enhance LLM performance on complex graph tasks. Results show that SSD improves the average passing rate of GPT-4, GPT-4o, Gemini-Pro and Claude-3-Sonnet by 8.38%, 6.78%, 29.28% and 25.28%, respectively.

Yue Huang, Yuchen Ma, Jiayi Ye et al.

Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmarks for this setting are limited: existing evaluations often focus on static prompts, isolated story generations, or post-hoc ratings, and therefore miss whether models can jointly manage story generation, long-context state and pacing, character simulation, empathic personalization, and story-grounded artifacts. We introduce NARRA-Gym, an executable evaluation environment that turns a sparse emotional seed into a complete interactive story episode and logs the full model-in-the-loop trajectory, including story construction, memory updates, planning, pacing interventions, and optional artifact synthesis. We evaluate nine frontier LLMs using a controlled LLM-as-judge sweep over eight benchmark personas and a human evaluation in which participants rate customized model outputs. Our results show substantial variation across models, personas, and evaluation dimensions: models that produce fluent stories can still fail on robustness, user experience, or resistance-sensitive personalization. These findings suggest that interactive narrative offers a useful benchmark for evaluating long-horizon, user-adaptive LLM behavior beyond isolated story quality.

Zichen Chen, Yunhao Luo, Misha Sra

As reliance on AI systems for decision-making grows, it becomes critical to ensure that human users can appropriately balance trust in AI suggestions with their own judgment, especially in high-stakes domains like healthcare. However, human + AI teams have been shown to perform worse than AI alone, with evidence indicating automation bias as the reason for poorer performance, particularly because humans tend to follow AI's recommendations even when they are incorrect. In many existing human + AI systems, decision-making support is typically provided in the form of text explanations (XAI) to help users understand the AI's reasoning. Since human decision-making often relies on System 1 thinking, users may ignore or insufficiently engage with the explanations, leading to poor decision-making. Previous research suggests that there is a need for new approaches that encourage users to engage with the explanations and one proposed method is the use of cognitive forcing functions (CFFs). In this work, we examine how various decision-support mechanisms impact user engagement, trust, and human-AI collaborative task performance in a diabetes management decision-making scenario. In a controlled experiment with 108 participants, we evaluated the effects of six decision-support mechanisms split into two categories of explanations (text, visual) and four CFFs. Our findings reveal that mechanisms like AI confidence levels, text explanations, and performance visualizations enhanced human-AI collaborative task performance, and improved trust when AI reasoning clues were provided. Mechanisms like human feedback and AI-driven questions encouraged deeper reflection but often reduced task performance by increasing cognitive effort, which in turn affected trust. Simple mechanisms like visual explanations had little effect on trust, highlighting the importance of striking a balance in CFF and XAI design.

Zichen Chen, Jiaao Chen, Jianda Chen et al.

Standard benchmarks fixate on how well large language model (LLM) agents perform in finance, yet say little about whether they are safe to deploy. We argue that accuracy metrics and return-based scores provide an illusion of reliability, overlooking vulnerabilities such as hallucinated facts, stale data, and adversarial prompt manipulation. We take a firm position: financial LLM agents should be evaluated first and foremost on their risk profile, not on their point-estimate performance. Drawing on risk-engineering principles, we outline a three-level agenda: model, workflow, and system, for stress-testing LLM agents under realistic failure modes. To illustrate why this shift is urgent, we audit six API-based and open-weights LLM agents on three high-impact tasks and uncover hidden weaknesses that conventional benchmarks miss. We conclude with actionable recommendations for researchers, practitioners, and regulators: audit risk-aware metrics in future studies, publish stress scenarios alongside datasets, and treat ``safety budget'' as a primary success criterion. Only by redefining what ``good'' looks like can the community responsibly advance AI-driven finance.

Yifan Li, Lichi Li, Anh Dao et al.

While Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reasoning. Existing embodied benchmarks largely focus on passive, static household environments and evaluate only isolated capabilities, failing to capture holistic performance in dynamic, real-world complexity. To fill this gap, we present IndustryNav, the first dynamic industrial navigation benchmark for active spatial reasoning. IndustryNav leverages 12 manually created, high-fidelity Unity warehouse scenarios featuring dynamic objects and human movement. Our evaluation employs a PointGoal navigation pipeline that effectively combines egocentric vision with global odometry to assess holistic local-global planning. Crucially, we introduce the "collision rate" and "warning rate" metrics to measure safety-oriented behaviors and distance estimation. A comprehensive study of nine state-of-the-art VLLMs (including models such as GPT-5-mini, Claude-4.5, and Gemini-2.5) reveals that closed-source models maintain a consistent advantage; however, all agents exhibit notable deficiencies in robust path planning, collision avoidance and active exploration. This highlights a critical need for embodied research to move beyond passive perception and toward tasks that demand stable planning, active exploration, and safe behavior in dynamic, real-world environment.

Zichen Chen, Jiefeng Chen, Sercan Ö. Arik et al.

Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation from natural language queries. However, current systems struggle with complex datasets containing multiple files and iterative refinement. Existing approaches, including simple single- or multi-agent systems, often oversimplify the task, focusing on initial query parsing while failing to robustly manage data complexity, code errors, or final visualization quality. In this paper, we reframe this challenge as a collaborative multi-agent problem. We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection. We formalize this pipeline, demonstrating how metadata-focused analysis bypasses token limits and quality-driven refinement ensures robustness. Extensive evaluations show CoDA achieves substantial gains in the overall score, outperforming competitive baselines by up to 41.5%. This work demonstrates that the future of visualization automation lies not in isolated code generation but in integrated, collaborative agentic workflows.

Jiao Peng, Feifan Wang, Zhongqiang Fu et al.

Recent years have witnessed the advancement of deep learning vision technologies and applications in the medical industry. Intelligent devices for special medication management are in great need of, which requires more precise detection algorithms to identify the specifications and locations. In this work, YOLO (You only look once) based object detectors are tailored for toxic and narcotic medications detection tasks. Specifically, a more flexible annotation with rotated degree ranging from $0^\circ$ to $90^\circ$ and a mask-mapping-based non-maximum suppression method are proposed to achieve a feasible and efficient medication detector aiming at arbitrarily oriented bounding boxes. Extensive experiments demonstrate that the rotated YOLO detectors are more suitable for identifying densely arranged drugs. The best shot mean average precision of the proposed network reaches 0.811 while the inference time is less than 300ms.