Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering

Video question answering requires models to ground language queries in visual evidence and, when necessary, reason over that evidence across time. Existing methods typically rely on long textual chain-of-thought rationales, even though many questions can be answered as soon as the relevant object, action, or frame is localized. We propose Dynamic Latent Reasoning (DyLaR), which first grounds a question in a short block of perception latents (continuous hidden states that encode query-relevant visual evidence), and then adaptively decides whether to append reasoning latents (continuous thoughts that reason over this evidence in latent space) before answering. DyLaR learns this behavior by grounding perception latents in verified visual evidence and distilling verified rationales into reasoning latents, followed by reinforcement learning that further refines when to reason. Across nine video benchmarks and four multimodal language model backbones, DyLaR improves average accuracy over same-backbone baselines while generating fewer than 20 tokens per query. On Qwen3-VL-4B, for example, DyLaR improves average accuracy over Qwen3-VL-4B-Thinking from 54.0 to 58.2 while reducing response length from 1,220.7 to 18.5 tokens per query. Ablations further show that grounded perception latents, rationale-supervised reasoning latents, and adaptive routing each improve accuracy.

SportD: Can VLMs Physically Strategize?

Vision--language models have become increasingly capable of interpreting visual scenes, but it remains unclear whether they can use information to make strategically effective decisions. We investigate this question in soccer, where models observe the seconds preceding an on-ball decision and must choose whether to shoot or pass to a specific teammate. Unlike conventional visual-understanding tasks, soccer enables decisions to be evaluated quantitatively by estimating the value of every available action. We introduce SportD, a benchmark comprising 478 on-ball decisions from the 2022 FIFA World Cup. Each model choice is evaluated against a possession-value model that estimates the action that most increases the attacking team's probability of scoring, allowing us to measure both optimal-action accuracy and the value forfeited by suboptimal decisions. Across three frontier VLMs, the best selects the highest-valued action on 31.4% of events, compared with 38.9% for the professional players, and all models incur significantly greater regret. Further analysis reveals a systematic preference for lower-variance and lower-reward actions: VLMs shoot less often and select substantially less progressive passes than either the optimal policy or the real players. The models also reproduce the player's specific action above chance even when that action is suboptimal, suggesting partial imitation of familiar play patterns rather than consistent evaluation of counterfactual alternatives. SportD provides a value-grounded testbed for measuring physical strategic reasoning in VLMs.

Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?

Rubric-based scoring has become a widely used paradigm in model evaluation, typically with LLM-as-a-Judge (LaaJ) for rubric scoring. However, the reliability of LaaJ for rubric scoring remains underexplored. This concern is especially pronounced in agentic scenarios, where long, complex outputs further challenge reliable scoring. To address this, we conduct a systematic meta-evaluation of LaaJ reliability for rubric verification. We introduce RuVerBench, the first benchmark for assessing LaaJ reliability in rubric verification for agentic scenarios. RuVerBench covers two prevalent agentic domains, deep research and agentic coding, with 2,458 instances, each containing a model-generated output, a rubric, and a human-annotated label indicating whether the output satisfies the rubric. Using RuVerBench, we evaluate numerous frontier LLMs and find that even the most advanced models achieve strong performance but still exhibit substantial noise. We further analyze the impact of key LaaJ strategies, including prompt design, batching, and majority voting, on rubric verification. We find that weaker models are more sensitive to prompt variations, batched verification presents a trade-off between accuracy and efficiency, and majority voting yields effective but diminishing returns. We have released our dataset and code to facilitate future research: https://github.com/THU-KEG/RuVerBench.

StoryAlign: Evaluating and Training Reward Models for Story Generation

Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, stories generated by LLMs still diverge from human-authored works regarding complex narrative structure and human-aligned preferences. A key reason is the absence of effective modeling of human story preferences, which are inherently subjective and under-explored. In this work, we systematically evaluate the modeling of human story preferences and introduce StoryRMB, the first benchmark for assessing reward models on story preferences. StoryRMB contains $1,133$ high-quality, human-verified instances, each consisting of a prompt, one chosen story, and three rejected stories. We find existing reward models struggle to select human-preferred stories, with the best model achieving only $66.3\%$ accuracy. To address this limitation, we construct roughly $100,000$ high-quality story preference pairs across diverse domains and develop StoryReward, an advanced reward model for story preference trained on this dataset. StoryReward achieves state-of-the-art (SoTA) performance on StoryRMB, outperforming much larger models. We also adopt StoryReward in downstream test-time scaling applications for best-of-n (BoN) story selection and find that it generally chooses stories better aligned with human preferences. We will release our dataset, model, and code to facilitate future research. Related code and data are available at https://github.com/THU-KEG/StoryReward.

SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports

Deeply understanding sports requires an intricate blend of fine-grained visual perception and rule-based reasoning - a challenge that pushes the limits of current multimodal models. To succeed, models must master three critical capabilities: perceiving nuanced visual details, applying abstract sport rule knowledge, and grounding that knowledge in specific visual evidence. Current sports benchmarks either cover single sports or lack the detailed reasoning chains and precise visual grounding needed to robustly evaluate these core capabilities in a multi-sport context. To address this gap, we introduce SportR, the first multi-sports large-scale benchmark designed to train and evaluate MLLMs on the fundamental reasoning required for sports intelligence. Our benchmark provides a dataset of 5,017 images and 2,101 videos. To enable granular evaluation, we structure our benchmark around a progressive hierarchy of question-answer (QA) pairs designed to probe reasoning at increasing depths - from simple infraction identification to complex penalty prediction. For the most advanced tasks requiring multi-step reasoning, such as determining penalties or explaining tactics, we provide 7,118 high-quality, human-authored Chain of Thought (CoT) annotations. In addition, our benchmark incorporates both image and video modalities and provides manual bounding box annotations to test visual grounding in the image part directly. Extensive experiments demonstrate the profound difficulty of our benchmark. State-of-the-art baseline models perform poorly on our most challenging tasks. While training on our data via Supervised Fine-Tuning and Reinforcement Learning improves these scores, they remain relatively low, highlighting a significant gap in current model capabilities. SportR presents a new challenge for the community, providing a critical resource to drive future research in multimodal sports reasoning.

DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning

Sports video understanding presents unique challenges, requiring models to perceive high-speed dynamics, comprehend complex rules, and reason over long temporal contexts. While Multimodal Large Language Models (MLLMs) have shown promise in genral domains, the current state of research in sports remains narrowly focused: existing approaches are either single-sport centric, limited to specific tasks, or rely on training-free paradigms that lack robust, learned reasoning process. To address this gap, we introduce DeepSport, the first end-to-end trained MLLM framework designed for multi-task, multi-sport video understanding. DeepSport shifts the paradigm from passive frame processing to active, iterative reasoning, empowering the model to ``think with videos'' by dynamically interrogating content via a specialized frame-extraction tool. To enable this, we propose a data distillation pipeline that synthesizes high-quality Chain-of-Thought (CoT) trajectories from 10 diverse data source, creating a unified resource of 78k training data. We then employ a two-stage training strategy, Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) with a novel gated tool-use reward, to optimize the model's reasoning process. Extensive experiments on the testing benchmark of 6.7k questions demonstrate that DeepSport achieves state-of-the-art performance, significantly outperforming baselines of both proprietary model and open-source models. Our work establishes a new foundation for domain-specific video reasoning to address the complexities of diverse sports.

FACTS: Fine-Grained Action Classification for Tactical Sports

Classifying fine-grained actions in fast-paced, close-combat sports such as fencing and boxing presents unique challenges due to the complexity, speed, and nuance of movements. Traditional methods reliant on pose estimation or fancy sensor data often struggle to capture these dynamics accurately. We introduce FACTS, a novel transformer-based approach for fine-grained action recognition that processes raw video data directly, eliminating the need for pose estimation and the use of cumbersome body markers and sensors. FACTS achieves state-of-the-art performance, with 90% accuracy on fencing actions and 83.25% on boxing actions. Additionally, we present a new publicly available dataset featuring 8 detailed fencing actions, addressing critical gaps in sports analytics resources. Our findings enhance training, performance analysis, and spectator engagement, setting a new benchmark for action classification in tactical sports.

SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) are advancing the ability to reason about complex sports scenarios by integrating textual and visual information. To comprehensively evaluate their capabilities, we introduce SPORTU, a benchmark designed to assess MLLMs across multi-level sports reasoning tasks. SPORTU comprises two key components: SPORTU-text, featuring 900 multiple-choice questions with human-annotated explanations for rule comprehension and strategy understanding. This component focuses on testing models' ability to reason about sports solely through question-answering (QA), without requiring visual inputs; SPORTU-video, consisting of 1,701 slow-motion video clips across 7 different sports and 12,048 QA pairs, designed to assess multi-level reasoning, from simple sports recognition to complex tasks like foul detection and rule application. We evaluate four prevalent LLMs mainly utilizing few-shot learning paradigms supplemented by chain-of-thought (CoT) prompting on the SPORTU-text part. We evaluate four LLMs using few-shot learning and chain-of-thought (CoT) prompting on SPORTU-text. GPT-4o achieves the highest accuracy of 71%, but still falls short of human-level performance, highlighting room for improvement in rule comprehension and reasoning. The evaluation for the SPORTU-video part includes 7 proprietary and 6 open-source MLLMs. Experiments show that models fall short on hard tasks that require deep reasoning and rule-based understanding. Claude-3.5-Sonnet performs the best with only 52.6% accuracy on the hard task, showing large room for improvement. We hope that SPORTU will serve as a critical step toward evaluating models' capabilities in sports understanding and reasoning.

Sports Intelligence: Assessing the Sports Understanding Capabilities of Language Models through Question Answering from Text to Video

Understanding sports is crucial for the advancement of Natural Language Processing (NLP) due to its intricate and dynamic nature. Reasoning over complex sports scenarios has posed significant challenges to current NLP technologies which require advanced cognitive capabilities. Toward addressing the limitations of existing benchmarks on sports understanding in the NLP field, we extensively evaluated mainstream large language models for various sports tasks. Our evaluation spans from simple queries on basic rules and historical facts to complex, context-specific reasoning, leveraging strategies from zero-shot to few-shot learning, and chain-of-thought techniques. In addition to unimodal analysis, we further assessed the sports reasoning capabilities of mainstream video language models to bridge the gap in multimodal sports understanding benchmarking. Our findings highlighted the critical challenges of sports understanding for NLP. We proposed a new benchmark based on a comprehensive overview of existing sports datasets and provided extensive error analysis which we hope can help identify future research priorities in this field.

Language and Multimodal Models in Sports: A Survey of Datasets and Applications

Recent integration of Natural Language Processing (NLP) and multimodal models has advanced the field of sports analytics. This survey presents a comprehensive review of the datasets and applications driving these innovations post-2020. We overviewed and categorized datasets into three primary types: language-based, multimodal, and convertible datasets. Language-based and multimodal datasets are for tasks involving text or multimodality (e.g., text, video, audio), respectively. Convertible datasets, initially single-modal (video), can be enriched with additional annotations, such as explanations of actions and video descriptions, to become multimodal, offering future potential for richer and more diverse applications. Our study highlights the contributions of these datasets to various applications, from improving fan experiences to supporting tactical analysis and medical diagnostics. We also discuss the challenges and future directions in dataset development, emphasizing the need for diverse, high-quality data to support real-time processing and personalized user experiences. This survey provides a foundational resource for researchers and practitioners aiming to leverage NLP and multimodal models in sports, offering insights into current trends and future opportunities in the field.