--Swarm intelligence describes how simple, decentralized agents can collectively produce complex behaviors. Recently, the concept of swarming has been extended to large language model (LLM)-powered systems, such as OpenAI's Swarm (OAS) framework, where agents coordinate through natural language prompts. Using OAS, we implement and compare classical and LLMbased versions of two well-established swarm algorithms: Boids and Ant Colony Optimization. Results indicate that while LLMpowered swarms can emulate swarm-like dynamics, they are constrained by substantial computational overhead. For instance, our LLM-based Boids simulation required roughly 300 more computation time than its classical counterpart, highlighting current limitations in applying LLM-driven swarms to real-time systems. W ARM intelligence continues to attract significant attention from researchers and engineers. In nature, swarming systems exist as flocks of birds, schools of fish, and colonies of ants, where they are characterized by local interactions among agents following simple rules. These interactions give rise to global patterns and adaptive behaviors that are greater than the sum of their parts [1]. However, the term "swarm" has recently been appropriated in novel contexts, such as OpenAI's Swarm (OAS) framework [2], where the dynamics and mechanisms differ from their traditional counterparts. This paper explores the differences, examining how the principles that define classical swarm algorithms translate, or fail to translate, within large language model (LLM)-based systems such as OAS, which is selected as a representative framework for LLM-powered swarms in this paper.

Robust unlearning is crucial for safely deploying large language models (LLMs) in environments where data privacy, model safety, and regulatory compliance must be ensured. Yet the task is inherently challenging, partly due to difficulties in reliably measuring whether unlearning has truly occurred. Moreover, fragmentation in current methodologies and inconsistent evaluation metrics hinder comparative analysis and reproducibility. To unify and accelerate research efforts, we introduce OpenUnlearning, a standardized and extensible framework designed explicitly for benchmarking both LLM unlearning methods and metrics. OpenUnlearning integrates 13 unlearning algorithms and 16 diverse evaluations across 3 leading benchmarks (TOFU, MUSE, and WMDP) and also enables analyses of forgetting behaviors across 450+ checkpoints we publicly release. Leveraging OpenUnlearning, we propose a novel meta-evaluation benchmark focused specifically on assessing the faithfulness and robustness of evaluation metrics themselves. We also benchmark diverse unlearning methods and provide a comparative analysis against an extensive evaluation suite. Overall, we establish a clear, community-driven pathway toward rigorous development in LLM unlearning research.

Learned optimizers have been an active research topic over the past decade, with increasing progress toward practical, general-purpose optimizers that can serve as drop-in replacements for widely used methods like Adam. However, recent advances -- such as VeLO, which was meta-trained for 4000 TPU-months -- remain largely inaccessible to the broader community, in part due to their reliance on JAX and the absence of user-friendly packages for applying the optimizers after meta-training. To address this gap, we introduce PyLO, a PyTorch-based library that brings learned optimizers to the broader machine learning community through familiar, widely adopted workflows. Unlike prior work focused on synthetic or convex tasks, our emphasis is on applying learned optimization to real-world large-scale pre-training tasks. Our release includes a CUDA-accelerated version of the small_fc_lopt learned optimizer architecture from (Metz et al., 2022a), delivering substantial speedups -- from 39.36 to 205.59 samples/sec throughput for training ViT B/16 with batch size 32. PyLO also allows us to easily combine learned optimizers with existing optimization tools such as learning rate schedules and weight decay. When doing so, we find that learned optimizers can substantially benefit. Our code is available at https://github.com/Belilovsky-Lab/pylo

This study critically examines the methodological rigor in credit card fraud detection research, revealing how fundamental evaluation flaws can overshadow algorithmic sophistication. Through deliberate experimentation with improper evaluation protocols, we demonstrate that even simple models can achieve deceptively impressive results when basic methodological principles are violated. Our analysis identifies four critical issues plaguing current approaches: (1) pervasive data leakage from improper preprocessing sequences, (2) intentional vagueness in methodological reporting, (3) inadequate temporal validation for transaction data, and (4) metric manipulation through recall optimization at precision's expense. We present a case study showing how a minimal neural network architecture with data leakage outperforms many sophisticated methods reported in literature, achieving 99.9\% recall despite fundamental evaluation flaws. These findings underscore that proper evaluation methodology matters more than model complexity in fraud detection research. The study serves as a cautionary example of how methodological rigor must precede architectural sophistication, with implications for improving research practices across machine learning applications.

Models that learn spurious correlations from training data often fail when deployed in new environments. While many methods aim to learn invariant representations to address this, they often underperform standard empirical risk minimization (ERM). We propose a data-centric alternative that shifts the focus from learning invariant representations to leveraging invariant data pairs -- pairs of samples that should have the same prediction. We prove that certain counterfactuals naturally satisfy this invariance property. Based on this, we introduce Noisy Counterfactual Matching (NCM), a simple constraint-based method that improves robustness by leveraging even a small number of \emph{noisy} counterfactual pairs -- improving upon prior works that do not explicitly consider noise. For linear causal models, we prove that NCM's test-domain error is bounded by its in-domain error plus a term dependent on the counterfactuals' quality and diversity. Experiments on synthetic data validate our theory, and we demonstrate NCM's effectiveness on real-world datasets.

As large language models (LLMs) are increasingly used in legal applications, current evaluation benchmarks tend to focus mainly on factual accuracy while largely neglecting important linguistic quality aspects such as clarity, coherence, and terminology. To address this gap, we propose three steps: First, we develop a regression model to evaluate the quality of legal texts based on clarity, coherence, and terminology. Second, we create a specialized set of legal questions. Third, we analyze 49 LLMs using this evaluation framework. Our analysis identifies three key findings: First, model quality levels off at 14 billion parameters, with only a marginal improvement of $2.7\%$ noted at 72 billion parameters. Second, engineering choices such as quantization and context length have a negligible impact, as indicated by statistical significance thresholds above 0.016. Third, reasoning models consistently outperform base architectures. A significant outcome of our research is the release of a ranking list and Pareto analysis, which highlight the Qwen3 series as the optimal choice for cost-performance tradeoffs. This work not only establishes standardized evaluation protocols for legal LLMs but also uncovers fundamental limitations in current training data refinement approaches. Code and models are available at: https://github.com/lyxx3rd/LegalEval-Q.

Multilingual large language models (LLMs) offer promising opportunities for cross-lingual information access, yet their use of factual knowledge remains highly sensitive to the input language. Prior work has addressed this through English prompting and evaluation, assuming that English-based reasoning is universally beneficial. In this work, we challenge that assumption by exploring factual knowledge transfer from non-English to English through the lens of Language and Thought Theory. We introduce Language-to-Thought (L2T) prompting, which aligns the model's internal ''thinking'' language with the source of knowledge. Across three languages and four models, L2T consistently outperforms English-based reasoning, reversing the expected advantage of English prompts. Our code is available at https://github.com/GeomeunByeol/Language2Thought.

Information seeking demands iterative evidence gathering and reflective reasoning, yet large language models (LLMs) still struggle with it in open-web question answering. Existing prompting and supervised fine-tuning (SFT) methods remain fixed by prompt rules or training corpora, and are usually benchmarked only on well-structured wiki sources, limiting real-world adaptability. We introduce WebPuzzle, a 24k-sample training and 275-sample test benchmark that evaluates information seeking on the live internet, across both wiki and open-domain queries. Leveraging 7k WebPuzzle instances, we develop DeepDiver, a reinforcement-learning (RL) framework that cultivates Search Intensity Scaling (SIS)-an emergent ability to escalate search frequency and depth instead of settling on overconfident, under-evidenced answers. With SIS, Qwen2.5-7B-Instruct and Pangu-7B-Reasoner attain performance on real-web tasks comparable to the 671B-parameter DeepSeek-R1. We detail DeepDiver's curriculum from cold-start SFT to a well designed RL procedure, and show that its seeking policy generalized from closed-ended queries to open-ended generation such as long-form writing. Our results advance adaptive information seeking in LLMs and provide a rigorous benchmark for future work.

In recent years, protein-text models have gained significant attention for their potential in protein generation and understanding. Current approaches focus on integrating protein-related knowledge into large language models through continued pretraining and multi-modal alignment, enabling simultaneous comprehension of textual descriptions and protein sequences. Through a thorough analysis of existing model architectures and text-based protein understanding benchmarks, we identify significant data leakage issues present in current benchmarks. Moreover, conventional metrics derived from natural language processing fail to accurately assess the model's performance in this domain. To address these limitations, we reorganize existing datasets and introduce a novel evaluation framework based on biological entities. Motivated by our observation, we propose a retrieval-enhanced method, which significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios. Our code and data can be seen at https://github.com/IDEA-XL/RAPM.

Text-embedded image generation plays a critical role in industries such as graphic design, advertising, and digital content creation. Text-to-Image generation methods leveraging diffusion models, such as TextDiffuser-2, have demonstrated promising results in producing images with embedded text. TextDiffuser-2 effectively generates bounding box layouts that guide the rendering of visual text, achieving high fidelity and coherence. However, existing approaches often rely on resource-intensive processes and are limited in their ability to run efficiently on both CPU and GPU platforms. To address these challenges, we propose a novel two-stage pipeline that integrates reinforcement learning (RL) for rapid and optimized text layout generation with a diffusion-based image synthesis model. Our RL-based approach significantly accelerates the bounding box prediction step while reducing overlaps, allowing the system to run efficiently on both CPUs and GPUs. Extensive evaluations demonstrate that our framework achieves comparable performance to TextDiffuser-2 in terms of text placement and image synthesis, while offering markedly faster runtime and increased flexibility. Our method produces high-quality images comparable to TextDiffuser-2, while being 42.29 times faster and requiring only 2 MB of CPU RAM for inference, unlike TextDiffuser-2's M1 model, which is not executable on CPU-only systems.