Evaluating large language models (LLMs) in complex decision-making is essential for advancing AI's ability for strategic planning and real-time adaptation. However, existing benchmarks for tasks like StarCraft II fail to capture the game's full complexity, such as its complete game context, diverse action spaces, and all playable races. To address this gap, we present SC2Arena, a benchmark that fully supports all playable races, low-level action spaces, and optimizes text-based observations to tackle spatial reasoning challenges. Complementing this, we introduce StarEvolve, a hierarchical framework that integrates strategic planning with tactical execution, featuring iterative self-correction and continuous improvement via fine-tuning on high-quality game-play data. Its key components include a Planner-Executor-V erifier structure to break down gameplay, and a scoring system for selecting high-quality training samples. Comprehensive analysis using SC2Arena provides valuable insights into developing generalist agents that were not possible with previous benchmarks. Experimental results also demonstrate that our proposed StarEvolve achieves superior performance in strategic planning. Our code, environment, and algorithms are publicly available.

Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies due to \textit{redundant} attention computations: while attention weights are often \textit{sparse}, all tokens consume \textit{equal} computational resources. In this paper, we reformulate traditional probabilistic sequence modeling as a \textit{supervised learning task}, enabling the separation of relevant and irrelevant tokens and providing a clearer understanding of redundancy. Based on this reformulation, we theoretically analyze attention sparsity, revealing that only a few tokens significantly contribute to predictions. Building on this, we formulate attention optimization as a linear coding problem and propose a \textit{group coding strategy}, theoretically showing its ability to improve robustness against random noise and enhance learning efficiency. Motivated by this, we propose \textit{Dynamic Group Attention} (DGA), which leverages the group coding to explicitly reduce redundancy by aggregating less important tokens during attention computation. Empirical results show that our DGA significantly reduces computational costs while maintaining competitive performance.Code is available at https://github.com/bolixinyu/DynamicGroupAttention.

The rapid rise of Generative AI (GenAI), particularly LLMs, poses concerns for journalistic integrity and authorship. This study examines AI-generated content across over 40,000 news articles from major, local, and college news media, in various media formats. Using three advanced AI-text detectors (e.g., Binoculars, Fast-Detect GPT, and GPTZero), we find substantial increase of GenAI use in recent years, especially in local and college news. Sentence-level analysis reveals LLMs are often used in the introduction of news, while conclusions usually written manually. Linguistic analysis shows GenAI boosts word richness and readability but lowers formality, leading to more uniform writing styles, particularly in local media.

In the domain of scientific machine learning, designing effective reward functions remains a challenge in reinforcement learning (RL), particularly in environments where task goals are difficult to specify numerically. Reward functions in existing work are predominantly based on heuristics, manual engineering, or task-specific tuning. In this work, we introduce a semantically aligned reinforcement learning method where rewards are computed by aligning the current state with a target semantic instruction using a Sentence-Bidirectional Encoder Representations from Transformers (SBERT). Instead of relying on manually defined reward functions, the policy receives feedback based on the reward, which is a cosine similarity between the goal textual description and the statement description in the episode. We evaluated our approach in several environments and showed that semantic reward can guide learning to achieve competitive control behavior, even in the absence of hand-crafted reward functions. Our study demonstrates a correlation between the language embedding space and the conventional Euclidean space. This framework opens new horizons for aligning agent behavior with natural language goals and lays the groundwork for a more seamless integration of larger language models (LLMs) and fluid control applications.

We introduce the concept of "Legal Zero-Days" as a novel risk vector for advanced AI systems. Legal Zero-Days are previously undiscovered vulnerabilities in legal frameworks that, when exploited, can cause immediate and significant societal disruption without requiring litigation or other processes before impact. We present a risk model for identifying and evaluating these vulnerabilities, demonstrating their potential to bypass safeguards or impede government responses to AI incidents. Using the 2017 Australian dual citizenship crisis as a case study, we illustrate how seemingly minor legal oversights can lead to large-scale governance disruption. We develop a methodology for creating "legal puzzles" as evaluation instruments for assessing AI systems' capabilities to discover such vulnerabilities. Our findings suggest that while current AI models may not reliably find impactful Legal Zero-Days, future systems may develop this capability, presenting both risks and opportunities for improving legal robustness. This work contributes to the broader effort to identify and mitigate previously unrecognized risks from frontier AI systems.

By virtue of its great utility in solving real-world problems, optimization modeling has been widely employed for optimal decision-making across various sectors, but it requires substantial expertise from operations research professionals. With the advent of large language models (LLMs), new opportunities have emerged to automate the procedure of mathematical modeling. This survey presents a comprehensive and timely review of recent advancements that cover the entire technical stack, including data synthesis and fine-tuning for the base model, inference frameworks, benchmark datasets, and performance evaluation. In addition, we conducted an in-depth analysis on the quality of benchmark datasets, which was found to have a surprisingly high error rate. We cleaned the datasets and constructed a new leaderboard with fair performance evaluation in terms of base LLM model and datasets. We also build an online portal that integrates resources of cleaned datasets, code and paper repository to benefit the community. Finally, we identify limitations in current methodologies and outline future research opportunities.

Modern vision-language models (VLMs) often fail at cultural competency evaluations and benchmarks. Given the diversity of applications built upon VLMs, there is renewed interest in understanding how they encode cultural nuances. While individual aspects of this problem have been studied, we still lack a comprehensive framework for systematically identifying and annotating the nuanced cultural dimensions present in images for VLMs. This position paper argues that foundational methodologies from visual culture studies (cultural studies, semiotics, and visual studies) are necessary for cultural analysis of images. Building upon this review, we propose a set of five frameworks, corresponding to cultural dimensions, that must be considered for a more complete analysis of the cultural competencies of VLMs.

We investigate the potential of large language models (LLMs) to serve as efficient simulators for agentic search tasks in reinforcement learning (RL), thereby reducing dependence on costly interactions with external search engines. To this end, we first quantify the intrinsic search capability of LLMs via structured prompting and repeated sampling, which we term Self-Search. Our results reveal that LLMs exhibit strong scaling behavior with respect to the inference budget, achieving high pass@k on question-answering benchmarks, including the challenging BrowseComp task. Building on these observations, we introduce Self-Search RL (SSRL), which enhances LLMs' Self-Search capability through format-based and rule-based rewards. SSRL enables models to iteratively refine their knowledge utilization internally, without requiring access to external tools. Empirical evaluations demonstrate that SSRL-trained policy models provide a cost-effective and stable environment for search-driven RL training, reducing reliance on external search engines and facilitating robust sim-to-real transfer. We draw the following conclusions: 1) LLMs possess world knowledge that can be effectively elicited to achieve high performance; 2) SSRL demonstrates the potential of leveraging internal knowledge to reduce hallucination; 3) SSRL-trained models integrate seamlessly with external search engines without additional effort. Our findings highlight the potential of LLMs to support more scalable RL agent training.

Accurate differentiation of brain tumor types on magnetic resonance imaging (MRI) is critical for guiding treatment planning in neuro-oncology. Recent advances in large language models (LLMs) have enabled visual question answering (VQA) approaches that integrate image interpretation with natural language reasoning. In this study, we evaluated GPT-4o, GPT-5-nano, GPT-5-mini, and GPT-5 on a curated brain tumor VQA benchmark derived from 3 Brain Tumor Segmentation (BraTS) datasets - glioblastoma (GLI), meningioma (MEN), and brain metastases (MET). Each case included multi-sequence MRI triplanar mosaics and structured clinical features transformed into standardized VQA items. Models were assessed in a zero-shot chain-of-thought setting for accuracy on both visual and reasoning tasks. Results showed that GPT-5-mini achieved the highest macro-average accuracy (44.19%), followed by GPT-5 (43.71%), GPT-4o (41.49%), and GPT-5-nano (35.85%). Performance varied by tumor subtype, with no single model dominating across all cohorts. These findings suggest that GPT-5 family models can achieve moderate accuracy in structured neuro-oncological VQA tasks, but not at a level acceptable for clinical use.

Large Language Models (LLMs) show potential as sequential decision-making agents, but their application is often limited due to a reliance on large, computationally expensive models. This creates a need to improve smaller models, yet existing post-training methods are designed for single-turn interactions and cannot handle credit assignment in multi-step agentic tasks. To address this, we introduce Multi-Step Group-Relative Policy Optimization (MS-GRPO), a new algorithm for post-training LLM agents, grounded in formal Text-Mediated Stochastic Game (TSMG) and Language-Agent Policy (LAP) frameworks. For credit assignment, MS-GRPO attributes the entire cumulative episode reward to each individual episode step. We supplement this algorithm with a novel absolute-advantage-weighted episode sampling strategy that we show improves training performance. We evaluate our approach by post-training a 3-billion parameter model on Snake and Frozen Lake. Our experiments demonstrate that the method is effective in improving decision-making performance: our post-trained 3B parameter model outperforms a 72B parameter baseline by 50% on the Frozen Lake task. This work demonstrates that targeted post-training is a practical and efficient alternative to relying on model scale for creating sequential decision-making agents using LLMs.