Kaixin Li

Kaixin Li, Qisheng Hu, Xu Zhao et al.

Code editing encompasses a variety of pragmatic tasks that developers deal with daily. Despite its relevance and practical usefulness, automatic code editing remains an underexplored area in the evolution of deep learning models, partly due to data scarcity. In this work, we explore the use of Large Language Models (LLMs) to edit code based on user instructions. Evaluated on a novel human-written execution-based benchmark dubbed EditEval, we found current models often struggle to fulfill the instructions. In light of this, we contribute InstructCoder, the first instruction-tuning dataset designed to adapt LLMs for general-purpose code editing, containing high-diversity code-editing tasks such as comment insertion, code optimization, and code refactoring. It consists of over 114,000 instruction-input-output triplets and covers multiple distinct code editing scenarios. The collection process starts with filtered commit data sourced from GitHub Python repositories as seeds. Subsequently, the dataset is systematically expanded through an iterative process, where both seed and generated tasks are used to prompt ChatGPT for more data. Our findings reveal that open-source LLMs fine-tuned on InstructCoder can significantly enhance the accuracy of code edits, exhibiting superior code-editing performance matching advanced proprietary LLMs. The datasets and the source code are publicly available at https://github.com/qishenghu/CodeInstruct.

Gailun Zeng, Ziyang Luo, Hongzhan Lin et al.

The ability of critique is vital for models to self-improve and serve as reliable AI assistants. While extensively studied in language-only settings, multimodal critique of Large Multimodal Models (LMMs) remains underexplored despite their growing capabilities in tasks like captioning and visual reasoning. In this work, we introduce MM-CRITIC, a holistic benchmark for evaluating the critique ability of LMMs across multiple dimensions: basic, correction, and comparison. Covering 8 main task types and over 500 tasks, MM-CRITIC collects responses from various LMMs with different model sizes and is composed of 4471 samples. To enhance the evaluation reliability, we integrate expert-informed ground answers into scoring rubrics that guide GPT-4o in annotating responses and generating reference critiques, which serve as anchors for trustworthy judgments. Extensive experiments validate the effectiveness of MM-CRITIC and provide a comprehensive assessment of leading LMMs' critique capabilities under multiple dimensions. Further analysis reveals some key insights, including the correlation between response quality and critique, and varying critique difficulty across evaluation dimensions. Our code is available at https://github.com/MichealZeng0420/MM-Critic.

Zixin Chen, Hongzhan Lin, Kaixin Li et al.

The proliferation of memes on social media necessitates the capabilities of multimodal Large Language Models (mLLMs) to effectively understand multimodal harmfulness. Existing evaluation approaches predominantly focus on mLLMs' detection accuracy for binary classification tasks, which often fail to reflect the in-depth interpretive nuance of harmfulness across diverse contexts. In this paper, we propose MemeArena, an agent-based arena-style evaluation framework that provides a context-aware and unbiased assessment for mLLMs' understanding of multimodal harmfulness. Specifically, MemeArena simulates diverse interpretive contexts to formulate evaluation tasks that elicit perspective-specific analyses from mLLMs. By integrating varied viewpoints and reaching consensus among evaluators, it enables fair and unbiased comparisons of mLLMs' abilities to interpret multimodal harmfulness. Extensive experiments demonstrate that our framework effectively reduces the evaluation biases of judge agents, with judgment results closely aligning with human preferences, offering valuable insights into reliable and comprehensive mLLM evaluations in multimodal harmfulness understanding. Our code and data are publicly available at https://github.com/Lbotirx/MemeArena.

Shaobo Wang, Yantai Yang, Qilong Wang et al.

Dataset Distillation (DD) aims to synthesize a small dataset capable of performing comparably to the original dataset. Despite the success of numerous DD methods, theoretical exploration of this area remains unaddressed. In this paper, we take an initial step towards understanding various matching-based DD methods from the perspective of sample difficulty. We begin by empirically examining sample difficulty, measured by gradient norm, and observe that different matching-based methods roughly correspond to specific difficulty tendencies. We then extend the neural scaling laws of data pruning to DD to theoretically explain these matching-based methods. Our findings suggest that prioritizing the synthesis of easier samples from the original dataset can enhance the quality of distilled datasets, especially in low IPC (image-per-class) settings. Based on our empirical observations and theoretical analysis, we introduce the Sample Difficulty Correction (SDC) approach, designed to predominantly generate easier samples to achieve higher dataset quality. Our SDC can be seamlessly integrated into existing methods as a plugin with minimal code adjustments. Experimental results demonstrate that adding SDC generates higher-quality distilled datasets across 7 distillation methods and 6 datasets.

Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin et al.

Computer-use agents (CUAs) hold great promise for automating complex desktop workflows, yet progress toward general-purpose agents is bottlenecked by the scarcity of continuous, high-quality human demonstration videos. Recent work emphasizes that continuous video, not sparse screenshots, is the critical missing ingredient for scaling these agents. However, the largest existing open dataset, ScaleCUA, contains only 2 million screenshots, equating to less than 20 hours of video. To address this bottleneck, we introduce CUA-Suite, a large-scale ecosystem of expert video demonstrations and dense annotations for professional desktop computer-use agents. At its core is VideoCUA, which provides approximately 10,000 human-demonstrated tasks across 87 diverse applications with continuous 30 fps screen recordings, kinematic cursor traces, and multi-layerfed reasoning annotations, totaling approximately 55 hours and 6 million frames of expert video. Unlike sparse datasets that capture only final click coordinates, these continuous video streams preserve the full temporal dynamics of human interaction, forming a superset of information that can be losslessly transformed into the formats required by existing agent frameworks. CUA-Suite further provides two complementary resources: UI-Vision, a rigorous benchmark for evaluating grounding and planning capabilities in CUAs, and GroundCUA, a large-scale grounding dataset with 56K annotated screenshots and over 3.6 million UI element annotations. Preliminary evaluation reveals that current foundation action models struggle substantially with professional desktop applications (~60% task failure rate). Beyond evaluation, CUA-Suite's rich multimodal corpus supports emerging research directions including generalist screen parsing, continuous spatial control, video-based reward modeling, and visual world models. All data and models are publicly released.

Kaixin Li, Yuchen Tian, Qisheng Hu et al.

Programming often involves converting detailed and complex specifications into code, a process during which developers typically utilize visual aids to more effectively convey concepts. While recent developments in Large Multimodal Models have demonstrated remarkable abilities in visual reasoning and mathematical tasks, there is little work on investigating whether these models can effectively interpret visual elements for code generation. To this end, we present MMCode, the first multi-modal coding dataset for evaluating algorithmic problem-solving skills in visually rich contexts. MMCode contains 3,548 questions and 6,620 images collected from real-world programming challenges harvested from 10 code competition websites, presenting significant challenges due to the extreme demand for reasoning abilities. Our experiment results show that current state-of-the-art models struggle to solve these problems. The results highlight the lack of powerful vision-code models, and we hope MMCode can serve as an inspiration for future works in this domain. The data and code are publicly available at https://github.com/likaixin2000/MMCode.

Aarash Feizi, Shravan Nayak, Xiangru Jian et al.

Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web and mobile interactions, high-quality resources for desktop environments are limited. To address this gap, we introduce GroundCUA, a large-scale desktop grounding dataset built from expert human demonstrations. It covers 87 applications across 12 categories and includes 56K screenshots, with every on-screen element carefully annotated for a total of over 3.56M human-verified annotations. From these demonstrations, we generate diverse instructions that capture a wide range of real-world tasks, providing high-quality data for model training. Using GroundCUA, we develop the GroundNext family of models that map instructions to their target UI elements. At both 3B and 7B scales, GroundNext achieves state-of-the-art results across five benchmarks using supervised fine-tuning, while requiring less than one-tenth the training data of prior work. Reinforcement learning post-training further improves performance, and when evaluated in an agentic setting on the OSWorld benchmark using o3 as planner, GroundNext attains comparable or superior results to models trained with substantially more data,. These results demonstrate the critical role of high-quality, expert-driven datasets in advancing general-purpose computer-use agents.

Anxing Xiao, Nuwan Janaka, Tianrun Hu et al.

Imagine a future when we can Zoom-call a robot to manage household chores remotely. This work takes one step in this direction. Robi Butler is a new household robot assistant that enables seamless multimodal remote interaction. It allows the human user to monitor its environment from a first-person view, issue voice or text commands, and specify target objects through hand-pointing gestures. At its core, a high-level behavior module, powered by Large Language Models (LLMs), interprets multimodal instructions to generate multistep action plans. Each plan consists of open-vocabulary primitives supported by vision-language models, enabling the robot to process both textual and gestural inputs. Zoom provides a convenient interface to implement remote interactions between the human and the robot. The integration of these components allows Robi Butler to ground remote multimodal instructions in real-world home environments in a zero-shot manner. We evaluated the system on various household tasks, demonstrating its ability to execute complex user commands with multimodal inputs. We also conducted a user study to examine how multimodal interaction influences user experiences in remote human-robot interaction. These results suggest that with the advances in robot foundation models, we are moving closer to the reality of remote household robot assistants.

Shaobo Wang, Xiangqi Jin, Ziming Wang et al.

Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational costs. Traditional data selection methods often require fine-tuning a scoring model on the target dataset, which is time-consuming and resource-intensive, or rely on heuristics that fail to fully leverage the model's predictive capabilities. To address these challenges, we propose Data Whisperer, an efficient, training-free, attention-based method that leverages few-shot in-context learning with the model to be fine-tuned. Comprehensive evaluations were conducted on both raw and synthetic datasets across diverse tasks and models. Notably, Data Whisperer achieves superior performance compared to the full GSM8K dataset on the Llama-3-8B-Instruct model, using just 10% of the data, and outperforms existing methods with a 3.1-point improvement and a 7.4$\times$ speedup. The code is available at https://github.com/gszfwsb/Data-Whisperer.

Shaobo Wang, Yantai Yang, Guo Chen et al.

Dataset Distillation (DD) seeks to create a compact dataset from a large, real-world dataset. While recent methods often rely on heuristic approaches to balance efficiency and quality, the fundamental relationship between original and synthetic data remains underexplored. This paper revisits knowledge distillation-based dataset distillation within a solid theoretical framework. We introduce the concepts of Informativeness and Utility, capturing crucial information within a sample and essential samples in the training set, respectively. Building on these principles, we define optimal dataset distillation mathematically. We then present InfoUtil, a framework that balances informativeness and utility in synthesizing the distilled dataset. InfoUtil incorporates two key components: (1) game-theoretic informativeness maximization using Shapley Value attribution to extract key information from samples, and (2) principled utility maximization by selecting globally influential samples based on Gradient Norm. These components ensure that the distilled dataset is both informative and utility-optimized. Experiments demonstrate that our method achieves a 6.1\% performance improvement over the previous state-of-the-art approach on ImageNet-1K dataset using ResNet-18.

Zixin Chen, Hongzhan Lin, Kaixin Li et al.

The proliferation of multimodal memes in the social media era demands that multimodal Large Language Models (mLLMs) effectively understand meme harmfulness. Existing benchmarks for assessing mLLMs on harmful meme understanding rely on accuracy-based, model-agnostic evaluations using static datasets. These benchmarks are limited in their ability to provide up-to-date and thorough assessments, as online memes evolve dynamically. To address this, we propose AdamMeme, a flexible, agent-based evaluation framework that adaptively probes the reasoning capabilities of mLLMs in deciphering meme harmfulness. Through multi-agent collaboration, AdamMeme provides comprehensive evaluations by iteratively updating the meme data with challenging samples, thereby exposing specific limitations in how mLLMs interpret harmfulness. Extensive experiments show that our framework systematically reveals the varying performance of different target mLLMs, offering in-depth, fine-grained analyses of model-specific weaknesses. Our code is available at https://github.com/Lbotirx/AdamMeme.

Jiacheng Liu, Chang Zou, Yuanhuiyi Lyu et al.

Diffusion models have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. These models face two fundamental challenges: strict temporal dependencies preventing parallelization, and computationally intensive forward passes required at each denoising step. Drawing inspiration from speculative decoding in large language models, we present SpeCa, a novel 'Forecast-then-verify' acceleration framework that effectively addresses both limitations. SpeCa's core innovation lies in introducing Speculative Sampling to diffusion models, predicting intermediate features for subsequent timesteps based on fully computed reference timesteps. Our approach implements a parameter-free verification mechanism that efficiently evaluates prediction reliability, enabling real-time decisions to accept or reject each prediction while incurring negligible computational overhead. Furthermore, SpeCa introduces sample-adaptive computation allocation that dynamically modulates resources based on generation complexity, allocating reduced computation for simpler samples while preserving intensive processing for complex instances. Experiments demonstrate 6.34x acceleration on FLUX with minimal quality degradation (5.5% drop), 7.3x speedup on DiT while preserving generation fidelity, and 79.84% VBench score at 6.1x acceleration for HunyuanVideo. The verification mechanism incurs minimal overhead (1.67%-3.5% of full inference costs), establishing a new paradigm for efficient diffusion model inference while maintaining generation quality even at aggressive acceleration ratios. Our codes have been released in Github: \textbf{https://github.com/Shenyi-Z/Cache4Diffusion}

Ruixi Wu, Shaobo Wang, Jiahuan Chen et al.

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic counterparts for efficient model training. However, existing DD methods exhibit substantial performance degradation on long-tailed datasets. We identify two fundamental challenges: heuristic design choices for distribution discrepancy measure and uniform treatment of imbalanced classes. To address these limitations, we propose Class-Aware Spectral Distribution Matching (CSDM), which reformulates distribution alignment via the spectrum of a well-behaved kernel function. This technique maps the original samples into frequency space, resulting in the Spectral Distribution Distance (SDD). To mitigate class imbalance, we exploit the unified form of SDD to perform amplitude-phase decomposition, which adaptively prioritizes the realism in tail classes. On CIFAR-10-LT, with 10 images per class, CSDM achieves a 14.0% improvement over state-of-the-art DD methods, with only a 5.7% performance drop when the number of images in tail classes decreases from 500 to 25, demonstrating strong stability on long-tailed data.

Kaixin Li, Ziyang Meng, Hongzhan Lin et al.

Recent advancements in Multi-modal Large Language Models (MLLMs) have led to significant progress in developing GUI agents for general tasks such as web browsing and mobile phone use. However, their application in professional domains remains under-explored. These specialized workflows introduce unique challenges for GUI perception models, including high-resolution displays, smaller target sizes, and complex environments. In this paper, we introduce ScreenSpot-Pro, a new benchmark designed to rigorously evaluate the grounding capabilities of MLLMs in high-resolution professional settings. The benchmark comprises authentic high-resolution images from a variety of professional domains with expert annotations. It spans 23 applications across five industries and three operating systems. Existing GUI grounding models perform poorly on this dataset, with the best model achieving only 18.9%. Our experiments reveal that strategically reducing the search area enhances accuracy. Based on this insight, we propose ScreenSeekeR, a visual search method that utilizes the GUI knowledge of a strong planner to guide a cascaded search, achieving state-of-the-art performance with 48.1% without any additional training. We hope that our benchmark and findings will advance the development of GUI agents for professional applications. Code, data and leaderboard can be found at https://gui-agent.github.io/grounding-leaderboard.

Jinghao Luo, Yuchen Tian, Chuxue Cao et al.

Large Language Model (LLM)-based agents have fundamentally reshaped artificial intelligence by integrating external tools and planning capabilities. While memory mechanisms have emerged as the architectural cornerstone of these systems, current research remains fragmented, oscillating between operating system engineering and cognitive science. This theoretical divide prevents a unified view of technological synthesis and a coherent evolutionary perspective. To bridge this gap, this survey proposes a novel evolutionary framework for LLM agent memory mechanisms, formalizing the development process into three stages: Storage (trajectory preservation), Reflection (trajectory refinement), and Experience (trajectory abstraction). We first formally define these three stages before analyzing the three core drivers of this evolution: the necessity for long-range consistency, the challenges in dynamic environments, and the ultimate goal of continual learning. Furthermore, we specifically explore two transformative mechanisms in the frontier Experience stage: proactive exploration and cross-trajectory abstraction. By synthesizing these disparate views, this work offers robust design principles and a clear roadmap for the development of next-generation LLM agents.

Juyoung Bae, Moo Hyun Son, Jiale Peng et al.

Digital crown design remains a labor-intensive bottleneck in restorative dentistry. We present CrownGen, a generative framework that automates patient-customized crown design using a denoising diffusion model on a novel tooth-level point cloud representation. The system employs two core components: a boundary prediction module to establish spatial priors and a diffusion-based generative module to synthesize high-fidelity morphology for multiple teeth in a single inference pass. We validated CrownGen through a quantitative benchmark on 496 external scans and a clinical study of 26 restoration cases. Results demonstrate that CrownGen surpasses state-of-the-art models in geometric fidelity and significantly reduces active design time. Clinical assessments by trained dentists confirmed that CrownGen-assisted crowns are statistically non-inferior in quality to those produced by expert technicians using manual workflows. By automating complex prosthetic modeling, CrownGen offers a scalable solution to lower costs, shorten turnaround times, and enhance patient access to high-quality dental care.

Xinbin Yuan, Jian Zhang, Kaixin Li et al.

Graphical User Interface (GUI) agents have made substantial strides in understanding and executing user instructions across diverse platforms. Yet, grounding these instructions to precise interface elements remains challenging, especially in complex, high-resolution, professional environments. Traditional supervised finetuning (SFT) methods often require large volumes of diverse data and exhibit weak generalization. To overcome these limitations, we introduce a reinforcement learning (RL) based framework that incorporates three core strategies: (1) seed data curation to ensure high quality training samples, (2) a dense policy gradient that provides continuous feedback based on prediction accuracy, and (3) a self evolutionary reinforcement finetuning mechanism that iteratively refines the model using attention maps. With only 3k training samples, our 7B-parameter model achieves state-of-the-art results among similarly sized models on three grounding benchmarks. Notably, it attains 47.3\% accuracy on the ScreenSpot-Pro dataset, outperforming much larger models, such as UI-TARS-72B, by a margin of 24.2\%. These findings underscore the effectiveness of RL-based approaches in enhancing GUI agent performance, particularly in high-resolution, complex environments.

Yutong Wang, Pengliang Ji, Chaoqun Yang et al.

The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances in reasoning models and shifts in scaling laws, we pioneer bringing test-time computation into LLM-as-a-Judge, proposing MCTS-Judge, a resource-efficient, System-2 thinking framework for code correctness evaluation. MCTS-Judge leverages Monte Carlo Tree Search (MCTS) to decompose problems into simpler, multi-perspective evaluations. Through a node-selection strategy that combines self-assessment based on historical actions in the current trajectory and the Upper Confidence Bound for Trees based on prior rollouts, MCTS-Judge balances global optimization and refinement of the current trajectory. We further designed a high-precision, unit-test-level reward mechanism to encourage the Large Language Model (LLM) to perform line-by-line analysis. Extensive experiments on three benchmarks and five LLMs demonstrate the effectiveness of MCTS-Judge, which improves the base model's accuracy from 41% to 80%, surpassing the o1-series models with 3x fewer tokens. Further evaluations validate the superiority of its reasoning trajectory in logic, analytics, thoroughness, and overall quality, while revealing the test-time scaling law of the LLM-as-a-Judge paradigm.

Yihang Wu, Xiao Cao, Kaixin Li et al.

In text-to-image generation tasks, the advancements of diffusion models have facilitated the fidelity of generated results. However, these models encounter challenges when processing text prompts containing multiple entities and attributes. The uneven distribution of attention results in the issues of entity leakage and attribute misalignment. Training from scratch to address this issue requires numerous labeled data and is resource-consuming. Motivated by this, we propose an attribution-focusing mechanism, a training-free phase-wise mechanism by modulation of attention for diffusion model. One of our core ideas is to guide the model to concentrate on the corresponding syntactic components of the prompt at distinct timesteps. To achieve this, we incorporate a temperature control mechanism within the early phases of the self-attention modules to mitigate entity leakage issues. An object-focused masking scheme and a phase-wise dynamic weight control mechanism are integrated into the cross-attention modules, enabling the model to discern the affiliation of semantic information between entities more effectively. The experimental results in various alignment scenarios demonstrate that our model attain better image-text alignment with minimal additional computational cost.

Yutong Wang, Pengliang Ji, Kaixin Li et al.

Large Language Reasoning Models have demonstrated remarkable success on static tasks, yet their application to multi-round agentic planning in interactive environments faces two fundamental challenges. First, the intractable credit assignment problem renders conventional reinforcement learning ineffective in sparse-reward settings. Second, the computational overhead of verbose, step-by-step reasoning histories is prohibitive. To address these challenges, we propose BPO, a three-stage framework (bootstrapping, extrapolation, and refinement) that establishes a self-improving data flywheel to develop robust reasoning models for long-horizon, sparse-reward environments. Our framework first bootstraps efficient reasoning using the proposed planning quaternions with long-short chain-of-thought fusion. It then extrapolates to out-of-distribution tasks through complexity-stratified curriculum learning. Finally, the model iteratively refines itself by learning exclusively on experiences selected via reward-gated rejection sampling. Experiments on ALFWorld, ScienceWorld, and WebShop demonstrate that our approach achieves state-of-the-art with significant token efficiency, providing a new recipe for reasoning models in agentic planning.

Shuai Bai, Yuxuan Cai, Ruizhe Chen et al.

We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows.

Xiaoxue Ren, Penghao Jiang, Kaixin Li et al.

Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, modern web applications demand visual understanding, dynamic content handling, and multi-step interactions that only computer-use agents (CUAs) can perform. Yet, their ability to discover and exploit vulnerabilities through graphical interfaces remains largely unexplored. We present HackWorld, the first framework for systematically evaluating CUAs' capabilities to exploit web application vulnerabilities via visual interaction. Unlike sanitized benchmarks, HackWorld includes 36 real-world applications across 11 frameworks and 7 languages, featuring realistic flaws such as injection vulnerabilities, authentication bypasses, and unsafe input handling. Using a Capture-the-Flag (CTF) setup, it tests CUAs' capacity to identify and exploit these weaknesses while navigating complex web interfaces. Evaluation of state-of-the-art CUAs reveals concerning trends: exploitation rates below 12% and low cybersecurity awareness. CUAs often fail at multi-step attack planning and misuse security tools. These results expose the current limitations of CUAs in web security contexts and highlight opportunities for developing more security-aware agents capable of effective vulnerability detection and exploitation.

Terry Yue Zhuo, Xiaolong Jin, Hange Liu et al.

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

Yuchen Tian, Kaixin Li, Hao Chen et al.

Large Language Models (LLMs) have recently demonstrated strong capabilities in translating natural language into database queries, especially when dealing with complex graph-structured data. However, real-world queries often contain inherent ambiguities, and the interconnected nature of graph structures can amplify these challenges, leading to unintended or incorrect query results. To systematically evaluate LLMs on this front, we propose a taxonomy of graph-query ambiguities, comprising three primary types: Attribute Ambiguity, Relationship Ambiguity, and Attribute-Relationship Ambiguity, each subdivided into Same-Entity and Cross-Entity scenarios. We introduce AmbiGraph-Eval, a novel benchmark of real-world ambiguous queries paired with expert-verified graph query answers. Evaluating 9 representative LLMs shows that even top models struggle with ambiguous graph queries. Our findings reveal a critical gap in ambiguity handling and motivate future work on specialized resolution techniques.

Wuxing Xu, Hao Fan, Kaixin Li et al.

More and more orgainizations and institutions make efforts on using external data to improve the performance of AI services. To address the data privacy and security concerns, federated learning has attracted increasing attention from both academia and industry to securely construct AI models across multiple isolated data providers. In this paper, we studied the efficiency problem of adapting widely used XGBoost model in real-world applications to vertical federated learning setting. State-of-the-art vertical federated XGBoost frameworks requires large number of encryption operations and ciphertext transmissions, which makes the model training much less efficient than training XGBoost models locally. To bridge this gap, we proposed a novel batch homomorphic encryption method to cut the cost of encryption-related computation and transmission in nearly half. This is achieved by encoding the first-order derivative and the second-order derivative into a single number for encryption, ciphertext transmission, and homomorphic addition operations. The sum of multiple first-order derivatives and second-order derivatives can be simultaneously decoded from the sum of encoded values. We are motivated by the batch idea in the work of BatchCrypt for horizontal federated learning, and design a novel batch method to address the limitations of allowing quite few number of negative numbers. The encode procedure of the proposed batch method consists of four steps, including shifting, truncating, quantizing and batching, while the decoding procedure consists of de-quantization and shifting back. The advantages of our method are demonstrated through theoretical analysis and extensive numerical experiments.