Searcharxiv⌕ Search

arXiv subjects

See-Kiong Ng

Publications and source records attributed to See-Kiong Ng.

At least 19 recordsLinked to original sources

Location Matters: Sparse Latent-Variance Attacks for Face Privacy against Diffusion Personalization

Text-to-image diffusion models can learn and reproduce an individual's identity from only a few reference photos, creating risks of unauthorized and misleading content generation. Proactive defenses address this risk by adding adversarial perturbations to facial images before release, thereby disrupting identity acquisition during downstream personalization. However, existing methods typically rely on dense $L_\infty$-bounded perturbations, whose accumulated distortions can become visible around facial structures. Recent methods improve protected-image quality, but often at the cost of reduced protection effectiveness. In this paper, we propose Sparse Encoder Attack on Latent Variance (SEAL), a sparse adversarial protection framework that modifies only 5% of the spatial locations in a facial image. SEAL combines a differentiable top-k masking scheme that jointly optimizes perturbation locations and values with a variance-oriented objective over the frozen VAE encoder's latent distribution to disrupt identity-consistent representations. A saliency-guided dispersion penalty further discourages perturbation concentration in perceptually salient facial regions. Experiments on CelebA-HQ and VGGFace2 show that SEAL achieves the best protected-image quality among the compared methods, exceeding 41 dB PSNR with 0.97 SSIM and at most 0.07 LPIPS, while reducing identity similarity to at most 0.15 after diffusion personalization. These results demonstrate that sparse location optimization enables strong identity protection while preserving high visual quality. Code and data are available at https://github.com/Lvxan/SEAL

cs.CV↗

TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning

Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently, large language models (LLMs) have emerged as a promising paradigm for TS quality assessment via pairwise comparison and per-dimension evaluation. However, existing approaches rely on manually predefined quality dimensions and purely text-based reasoning, leaving it unknown whether LLMs can identify truly relevant quality dimensions or perform grounded and quantitative quality comparisons. To investigate this, we construct TSQBench, a dedicated benchmark for evaluating LLMs on two progressive capabilities: (i) understanding and identifying relevant quality dimensions, and (ii) performing quality comparison under specific dimensions. Our analysis reveals that current LLMs consistently struggle with both dimension identification and evidence-grounded quality comparison. To address these limitations, we propose TSQAgent, a novel agentic reasoning framework for TS quality rating consisting of three collaborative roles: Perceiver for focused dimension selection, Inspector for dimension-wise quantitative analysis, and Adjudicator that aggregates and refines the final judgment. In particular, we introduce an agentic reasoning strategy that instills the ability to identify and prioritize the most relevant quality dimensions, and further propose an agent workflow equipped with external analytical tools to enable precise quantitative comparisons over selected dimensions. Experiments on both the proposed benchmark and eleven real-world datasets demonstrate that our framework not only substantially improves LLMs' capabilities in quality understanding and quantitative comparison but also effectively translates these improvements into better quality-aware data selection, leading to enhanced downstream performance and data efficiency.

cs.AI↗

CoworkOS:Scaling Agent Coworkers for Real-world Automation

Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-quality delivery on complex productivity tasks and continued monitoring and decision-making over long horizons, a combination that remains an open challenge. We introduce CoworkOS, a general-purpose harness for long-horizon work that separates task strategy from execution management: the model decides actions, delegation, and acceptance, while the runtime maintains state and feedback. Its three-layer architecture enables direct execution or delegation to Subagents, synchronously or asynchronously, under stable responsibilities. Through a shared application layer, humans and agents inspect and revise the same evolving documents, presentations, CAD models, and Blender scenes, so human-in-the-loop participation can enter both through conversation and through direct modification of the work itself. To sustain continuity across agents and sessions, CoworkOS further introduces hierarchical workspaces and persistent semantic memory, so working files, key decisions, and long-running Job logs remain shareable, reusable, and resumable after interruption. Across 12 benchmarks and 6 categories of real-world applications, CoworkOS proves highly competitive with frontier agent applications such as Codex and DeepSeek Harness. As a sustained-work case study, CoworkOS uses GLM-5.3 as its backbone to conduct RSI-driven automated post-training on Qwen3.6-35B-A3B. Over five rounds, the model's average score across eight benchmarks rose from 33.19 to 42.95 (+9.76). Looking ahead, we believe CoworkOS opens a meaningful path toward general cowork-agent intelligence.

cs.AI↗

CodeArena: A Collective Evaluation Platform for LLM Code Generation

Large Language Models (LLMs) have reshaped code generation by synergizing their exceptional comprehension of natural language and programming syntax, thereby substantially boosting developer productivity. These advancements have prompted numerous efforts to quantitatively evaluate their coding capabilities. However, persistent challenges, such as benchmark leakage, data dissipation, and limited system accessibility, continue to impede a timely and accurate assessment. To address these limitations, we introduce CodeArena, an online evaluation framework tailored for LLM code generation. The key innovation is a collective evaluation mechanism, which dynamically recalibrates individual model scores based on the holistic performance of all participating models, mitigating score biases caused by widespread benchmark leakage. In addition, CodeArena ensures open access to all submitted solutions and test cases and provides automation-friendly APIs to streamline the code evaluation workflow. Our main contributions are: (1) a collective evaluation system for unbiased assessment, (2) a public repository of solutions and test cases, and (3) automation-ready APIs for seamless integration.

cs.SE↗

Dual Exam: Controlled Evaluation of Multimodal Agents and World Models

World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction requires separate evidence about action selection and state evolution. We introduce Dual Exam, which tests Agents under fixed environment response mechanisms and World Models under fixed action interventions across physical, digital, social, and scientific domains. The Agent track compares 10 configurations on 1,088 items in 15 reporting categories. The World Model track contains 400 cases across eight scenarios; 15 configurations have full coverage and one covers six scenarios. GPT 6 Astra leads the case-weighted Agent Index at 31.3, and GPT-Image-2 leads the full-coverage WM Overall at 21.7. These scores use different tasks and metrics and are not directly comparable. A 150-case pilot of one coupled pairing records zero task successes and motivates component-level diagnosis. Results reveal uneven task performance and failures to preserve task-relevant state. Their value for predicting coupled success or sustained reciprocal learning remains to be established.

cs.AI↗

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first multi-language benchmark designed to measure the efficiency of LLM-generated code. EffiBench-X supports Python, C++, Java, JavaScript, Ruby, and Golang. It comprises competitive programming tasks with human-expert solutions as efficiency baselines. Evaluating state-of-the-art LLMs on EffiBench-X reveals that while models generate functionally correct code, they consistently underperform human experts in efficiency. Even the most efficient LLM-generated solutions (Qwen3-32B) achieve only around \textbf{62\%} of human efficiency on average, with significant language-specific variations. LLMs show better efficiency in Python, Ruby, and JavaScript than in Java, C++, and Golang. For instance, DeepSeek-R1's Python code is significantly more efficient than its Java code. These results highlight the critical need for research into LLM optimization techniques to improve code efficiency across diverse languages. The dataset and evaluation infrastructure are submitted and available at https://github.com/EffiBench/EffiBench-X.git and https://huggingface.co/datasets/EffiBench/effibench-x.

cs.CL↗

Uncovering Shortcut Amplification in Video RLVR through the Lens of Perceptual Uncertainty Collapse

Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for enhancing the video reasoning capability of Large Multimodal Models (LMMs). Despite its empirical effectiveness, we show that outcome-level optimization can introduce an undesirable shortcut amplification effect, whereby models increasingly favor text-prior answers even when they are not supported by the visual evidence. To characterize this behavior, we investigate the training dynamics of video RLVR through the lens of perceptual uncertainty, analyzing how predictive uncertainty evolves under video-conditioned and text-only contexts. Our analysis identifies a perceptual uncertainty collapse phenomenon, in which RL training continuously sharpens the model's answer distribution while the uncertainty reduction attributable to visual evidence progressively diminishes. A further gradient-direction analysis reveals that such confidence enhancement becomes increasingly less aligned with visually grounded uncertainty reduction and is instead dominated by text-prior compression. Motivated by these findings, we propose Bifocal Self-distillation Policy Optimization (BSPO), a self-distillation framework that regulates policy updates with two complementary distributional signals. Specifically, BSPO derives empirical reasoning principles from intra-group correct and incorrect rollouts to identify reasoning-sensitive tokens, and introduces shortcut-aware visual perturbation to penalize predictions that remain invariant when task-relevant visual evidence is weakened. By adaptively reweighting the original RL advantage, BSPO preserves the task-solving benefits of RLVR while promoting updates that are both reasoning-sensitive and visually grounded. Extensive experiments validate the effectiveness of BSPO in improving video reasoning performance and strengthening visual faithfulness.

cs.CV↗

Last Secure Code Benchmark: Is the Code You Vibe Secure?

AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce the Last Secure Code Benchmark, a comprehensive evaluation of secure code generation by coding agents. Built from 150 real vulnerabilities, its 450 tasks span seven widely used languages (Java, C, C++, JavaScript, Python, PHP, and Go), 24 CWEs including 21 of the 2025 CWE Top 25 and 8 of the Top 10 KEV weaknesses, more than any benchmark we compare with, and three vibe-coding scenarios: filling in a function, writing a file, and building a repository's source tree from scratch. Every task asks only for functionality, through a specification that never mentions security, and hidden functional and security tests grade the result. Across six frontier agents, 73.6% to 91.3% of tasks pass functionally, yet even the strongest, Claude Fable 5, produces code that is both functional and secure for only 25.1% of tasks, and the others for 16.4% to 24.7%. The best model only passes 12% of the vulnerability scenarios across all vibe coding setting, posing strong concern on the security of the code written by vibe coding.

cs.CR↗

Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction

Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar that reaches a vulnerable path, construct a proof-of-conceptv(PoC), and verify that the crash disappears on the patched build. Recent LLM agents can often execute these steps when the approach is correct, yet they still fail by choosing the wrong strategy. This paper argues that strategy, rather than the full action trajectory, is the right learning unit for such SE agents: it is compact enough to optimize, concrete enough to guide execution, and stable enough to store and reuse across attempts. We present Mastermind, a dual-loop framework that separates transferable strategy learning from task-specific experience. A trainable planner learns reusable vulnerability-reproduction strategies through SFT and milestone-based GRPO, while an experience loop maintains task-local strategy records that guide subsequent attempts. The planner is trained independently of the executor, allowing strategy learning to improve multiple frozen executors without modifying their action-generation capability. We evaluate Mastermind on CyberGym using 260 training tasks and 200 held-out evaluation tasks. With GPT-5.5 as the frozen executor, Mastermind achieves an 84.5% pass rate, outperforming open-book PoC context (60.0%), Best-of-8 sampling (63.0%), and iterative improvement (77.0%). The same planner also improves GPT-5.4 mini and GLM~5.1 from 45.0% and 58.5% to 60.0% and 71.0%. These results demonstrate that learning high-level strategies is an effective and transferable mechanism for improving repository-scale SE agents.

cs.AI↗

Collective Bias Mitigation via Model Routing and Collaboration

Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment. Despite recent advances, LLMs often perpetuate or amplify bias embedded in their training data, posing challenges to fairness. While self-debiasing encourages an LLM to identify and correct its own biases, relying on a single model's intrinsic knowledge may be insufficient to address deeply ingrained stereotypes. To address this limitation, we introduce Collective Bias Mitigation (CBM), a framework that alleviates bias by learning fine-grained model behavior and fostering knowledge sharing among diverse LLMs. This work is the first to systematically explore the effective selection and organization of distinct LLMs to cultivate fairer LLM responses. Experiments show CBM substantially outperforms standalone baselines (e.g., in the top-7 setting, Committee lowers the age bias score from 0.25 to 0.10). Our Debating and Committee topologies achieve substantial bias reduction, with the latter balancing mitigation effectiveness and inference cost, highlighting the potential of CBM for fairer LLMs.

cs.CL↗

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift

Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore, we study W2S preference learning under zero-shot distribution shift and find that strong students trained on weak preference labels can appear successful in-distribution while failing to transfer across preference datasets. We provide evidence for a representational failure mode in which weak-supervised fine-tuning can pull the strong model toward source-domain features instead of maintaining broadly transferable preference representations. To mitigate this, we propose Representation Anchoring (Anchor), a simple yet effective regularizer that constrains excessive drift from the pretrained strong model's representation space during fine-tuning, while still allowing task-relevant adaptation. Across preference domains, datasets, and model families, Anchor consistently improves out-of-distribution transfer while maintaining competitive in-distribution performance. Together, our evaluation protocol, transfer-aware metrics, and method expose hidden brittleness in current W2S reward modeling and provide a practical path toward more robust preference transfer.

cs.CL↗

Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents

We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire information that improves future decision-making. In this regard, we first identify two fundamental bottlenecks that hinder this capability and then propose \ours, a novel method designed to instill and refine proactive exploration. Specifically, \ours\ consists of two components: (1) Exploratory Data Construction, which synthesizes exploration-rich trajectories to mitigate the hindsight bias of standard demonstrations; and (2) RL Optimization with Contrastive Signal Guidance, which leverages contrastive trajectory pairs to distinguish productive exploration from redundant wandering. Extensive experiments demonstrate the effectiveness of \ours\ and provide insights into the characteristics of proactive exploration. Our code is available at: https://github.com/GuanZhizhao/SAFARI.

cs.AI↗

Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning

In this paper, we propose the first VL\underline{\textbf{M}} \underline{\textbf{a}}gentic \underline{\textbf{r}}easoning framework for few-\underline{\textbf{s}}hot multimodal \underline{\textbf{T}}ime \underline{\textbf{S}}eries \underline{\textbf{C}}lassification (\textsc{MarsTSC}), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agentic reasoning. The framework comprises three collaborative roles: i) Generator conducts reliable classification via reasoning; ii) Reflector diagnoses the root causes of reasoning errors to yield discriminative insights targeting the temporal features overlooked by Generator; iii) Modifier applies verified updates to the knowledge bank to prevent context collapse. We further introduce a test-time update strategy to enable cautious, continuous knowledge bank refinement to mitigate few-shot bias and distribution shift. Extensive experiments across 12 mainstream time series benchmark datasets demonstrate that \method{} delivers substantial and consistent performance gains across 5 VLM backbones, outperforming both classical and foundation model-based time series baselines under few-shot conditions, while producing interpretable rationales that ground each classification decision in human-readable feature evidence. Code is available at https://github.com/HuangJW0821/MarsTSC.

cs.AI↗

GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction

Agentic Workflows (AWs) have emerged as a promising paradigm for solving complex tasks. However, automatically generating high-quality AWs remains expensive because AW optimization requires evaluating a large number of candidate AWs via execution, resulting in high computational cost and latency. Recently, AW performance prediction has become a hot research topic to avoid costly execution-based evaluation, but existing methods primarily use Graph Neural Networks (GNNs) to model workflow structures and insufficiently capture the semantic relationships among agents. To address this limitation, we propose GLOW, a unified framework for AW performance prediction that combines the graph-structure modeling ability of GNNs with the topology-aware semantic encoding capability of LLMs. Specifically, a graph-oriented LLM is first built through instruction-tuning on graph understanding tasks to extract topology-aware semantic representations from descriptive text of AWs. Meanwhile, a GNN explicitly models the structural information of AWs and produces corresponding structural representations. The semantic and structural representations are then fused in a shared latent space using a Transformer-based fusion module. A contrastive learning strategy is further introduced to learn more discriminative representations for AWs. Experiments on the FLORA-Bench benchmark demonstrate that GLOW consistently outperforms state-of-the-art baselines in both prediction accuracy and ranking utility. Moreover, when integrated into the AFLOW, an automatic AW generation framework, GLOW reduces optimization time by 98.7% with only a 0.031 average score decrease across three datasets, showing its effectiveness as an efficient surrogate evaluator for AW optimization.

cs.LG↗

Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search

We investigate the role of conversational context modeling in user preference tracking for Conversational Recommendation Systems (CRSs). In this regard, we propose DREAMS, a novel tree-structured context modeling framework that explicitly captures user preference evolution throughout multi-turn interactions. DREAMS introduces two specialized node types to support the two fundamental objectives of CRSs: preference elicitation and preference exploitation. Specifically, elicitation nodes leverage Monte Carlo Tree Search (MCTS) to strategically explore conversational actions and infer latent user preferences, while exploitation nodes employ LLM-based refinement to transform the tracked preference state into structured retrieval queries for recommendation. Extensive experiments on benchmark datasets demonstrate the effectiveness of DREAMS and its design.

cs.IR↗

Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles

Benchmarks for LLM-generated GPU kernels decide correctness with a few random inputs and a loose floating-point tolerance, and their verdicts now feed leaderboards and reinforcement-learning rewards. Recent work agrees these checkers are weak and patches them by hand---extra input distributions, fuzzing recipes, tighter tolerances---with no way to \emph{measure} whether any patch suffices. We introduce mutation analysis as an adequacy metric for kernel-benchmark oracles: deterministic rules inject 10{,}303 compilable faults into verified CUDA implementations of 188 KernelBench problems, 7{,}384 of them with an independent kill witness; any test protocol is scored by the fraction it detects. The official check misses \textbf{one in six} witnessed faults (16.9%), deterministically, and the misses are skewed by family: 8.7% of arithmetic faults escape, but 78.6% of precision faults do. The metric explains why (a tolerance blind band growing with reduction size; a measured ceiling on input aggressiveness set by legitimate floating-point variance), audits the strongest existing patch (KernelBench-Verified's gain splits into $+4.0$ points from hidden inputs and $+4.5$ from tighter tolerance, a split its authors could not compute), and exposes a published fuzzing recipe that rejects \emph{correct} kernels 107 times. Optimizing suites over the kill matrix reaches 98.0% detection with two inputs per problem (94.8% held-out), and the measurement's fault taxonomy teaches a test generator more than the raw faults themselves. Across 48 whole architectures, the blindness grows with scale, concentrating in deep homogeneous pipelines, and two problems prove unrefereeable: their official references violate the benchmark's own tolerance against fp64. We release everything as \href{https://huggingface.co/datasets/Elfsong/KernelBench-M}{KernelBench-M}.

cs.LG↗

FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search

Agentic search requires language model agents to explore many sources and answer complex information-seeking questions. Scaling test-time compute is a promising way to improve these agents, but current approaches can fail, because correct answers are often sparse and score-based selection depends on model calibration. We propose FineVerify, a fine-grained self-verification framework that decomposes each question into checkable sub-questions, verifies sampled candidates against each sub-question, and selects the candidate with the highest aggregated score. This per-check structure turns selection into simpler local judgments and produces scores under the same explicit criteria. Across four agentic search benchmarks and two models, FineVerify consistently outperforms standard scaling baselines. With only four sampled trajectories, it improves GPT-5-mini by 8.2 accuracy points and Gemini-3-flash by 5.6% on average. With 12 samples, FineVerify enables GPT-5-mini to surpass frontier GPT-5 on BrowseComp-Plus. Beyond accuracy, FineVerify produces interpretable verification traces that help audit benchmark errors, suggesting broader applications for inspecting agentic search systems. Code and data are available at https://github.com/XuZhao0/fineverify

cs.CL↗

Self-Evolving World Models for LLM Agent Planning

World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unreliable foresight can be ignored, misused, or even degrade downstream decision-making. In this paper, we introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen. WorldEvolver integrates three modules: (i) Episodic Memory, which exploits real action transitions through retrieval-based simulation; (ii) Semantic Memory, which extracts persistent heuristic rules from prediction-observation mismatches; and (iii) Selective Foresight, which filters low-confidence predictions before integrating them into agent reasoning context. We evaluate WorldEvolver on ALFWorld and ScienceWorld, measuring world model prediction accuracy on Word2World and downstream agent success rate on AgentBoard. Extensive experiments show that WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate, demonstrating that test-time memory revision enhances both predictive fidelity and planning performance.

cs.AI↗