Chenzhuo Zhao

Youling Huang, Guanqiao Chen, Junchi Yao et al.

World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and offline evaluation. In text-based environments, world models are typically evaluated and trained with single-step metrics such as Exact Match, aiming to improve the similarity between predicted and real-world states, but such metrics have been shown to be insufficient for capturing actual agent behavior. To address this issue, we introduce a new behavior-aligned training paradigm aimed at improving the functional consistency between the world model and the real environment. This paradigm focuses on optimizing a tractable step-level metric named Behavior Consistency Reward (BehR), which measures how much the likelihood of a logged next action changes between the real state and the world-model-predicted state under a frozen Reference Agent. Experiments on WebShop and TextWorld show that BehR-based training improves long-term alignment in several settings, with the clearest gains in WebShop and less movement in near-ceiling regimes, while preserving or improving single-step prediction quality in three of four settings. World models trained with BehR also achieve lower false positives in offline surrogate evaluation and show modest but encouraging gains in inference-time lookahead planning.

You Hu, Chenzhuo Zhao, Changfa Mo et al.

Modern multimodal generators can now produce scientific figures at near-publishable quality, creating a new challenge for visual forensics and research integrity. Unlike conventional AI-generated natural images, scientific figures are structured, text-dense, and tightly aligned with scholarly semantics, making them a distinct and difficult detection target. However, existing AI-generated image detection benchmarks and methods are almost entirely developed for open-domain imagery, leaving this setting largely unexplored. We present the first benchmark for AI-generated scientific figure detection. To construct it, we develop an agent-based data pipeline that retrieves licensed source papers, performs multimodal understanding of paper text and figures, builds structured prompts, synthesizes candidate figures, and filters them through a review-driven refinement loop. The resulting benchmark covers multiple figure categories, multiple generation sources and aligned real--synthetic pairs. We benchmark representative detectors under zero-shot, cross-generator, and degraded-image settings. Results show that current methods fail dramatically in zero-shot transfer, exhibit strong generator-specific overfitting, and remain fragile under common post-processing corruptions. These findings reveal a substantial gap between existing AIGI detection capabilities and the emerging distribution of high-quality scientific figures. We hope this benchmark can serve as a foundation for future research on robust and generalizable scientific-figure forensics. The dataset is available at https://github.com/Joyce-yoyo/SciFigDetect.

Chenzhuo Zhao, Xinda Wang, Yue Huang et al.

While large language models (LLMs) have demonstrated remarkable performance on high-level semantic tasks, they often struggle with fine-grained, token-level understanding and structural reasoning--capabilities that are essential for applications requiring precision and control. We introduce TASE, a comprehensive benchmark designed to evaluate LLMs' ability to perceive and reason about token-level information across languages. TASE covers 10 tasks under two core categories: token awareness and structural understanding, spanning Chinese, English, and Korean, with a 35,927-instance evaluation set and a scalable synthetic data generation pipeline for training. Tasks include character counting, token alignment, syntactic structure parsing, and length constraint satisfaction. We evaluate over 30 leading commercial and open-source LLMs, including O3, Claude 4, Gemini 2.5 Pro, and DeepSeek-R1, and train a custom Qwen2.5-14B model using the GRPO training method. Results show that human performance significantly outpaces current LLMs, revealing persistent weaknesses in token-level reasoning. TASE sheds light on these limitations and provides a new diagnostic lens for future improvements in low-level language understanding and cross-lingual generalization. Our code and dataset are publicly available at https://github.com/cyzcz/Tase .

Xinda Wang, Zhengxu Hou, Yangshijie Zhang et al.

Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that require either annotated data or powerful closed-source models. Inspired by recent work on unsupervised reinforcement learning for mathematical reasoning using confidence-based endogenous rewards, we investigate whether this principle can be adapted to open-ended writing tasks. We find that directly applying confidence rewards leads to Triviality Bias: the policy collapses toward high-probability outputs, reducing diversity and meaningful content. We propose TCER (Triviality Corrected Endogenous Reward), which addresses this bias by rewarding the relative information gain between a specialist policy and a generalist reference policy, modulated by a probability-dependent correction mechanism. Across multiple writing benchmarks and model architectures, TCER achieves consistent improvements without external supervision. Furthermore, TCER also transfers effectively to mathematical reasoning, validating the generality of our approach across different generation tasks.

Chenzhuo Zhao, Ziqian Liu, Xinda Wang et al.

Prompt optimization is a practical and widely applicable alternative to fine tuning for improving large language model performance. Yet many existing methods evaluate candidate prompts by sampling full outputs, often coupled with self critique or human annotated preferences, which limits scalability, especially for smaller models or models that are not instruction tuned. We present PMPO (Probabilistic Metric Prompt Optimization), a unified framework that uses token level cross entropy as a direct, lightweight evaluation signal. PMPO locates low quality prompt segments via a masking based analysis and iteratively rewrites them to propose improved variants. Crucially, during evaluation, PMPO selects among variants by minimizing loss in a single forward pass, eliminating output sampling and human or judge based scoring for selection while still using standard generation only to propose rewrites. This unified, loss based strategy supports both supervised and preference based tasks. Across model sizes and datasets, PMPO outperforms prior prompt optimizers: it achieves the highest average accuracy on BBH, performs strongly on GSM8K and AQUA RAT, and raises AlpacaEval 2.0 win rates by over 19 points. These results demonstrate PMPO's effectiveness, efficiency, and broad applicability.