Stack Overflow (SO), a leading online community forum, is a rich source of software development knowledge. However, locating architectural knowledge, such as architectural solutions remains challenging due to the overwhelming volume of unstructured content and fragmented discussions. Developers must manually sift through posts to find relevant architectural insights, which is time-consuming and error-prone. This study introduces ArchISMiner, a framework for mining architectural knowledge from SO. The framework comprises two complementary components: ArchPI and ArchISPE. ArchPI trains and evaluates multiple models, including conventional ML/DL models, Pre-trained Language Models (PLMs), and Large Language Models (LLMs), and selects the best-performing model to automatically identify Architecture-Related Posts (ARPs) among programming-related discussions. ArchISPE employs an indirect supervised approach that leverages diverse features, including BERT embeddings and local TextCNN features, to extract architectural issue-solution pairs. Our evaluation shows that the best model in ArchPI achieves an F1-score of 0.960 in ARP detection, and ArchISPE outperforms baselines in both SE and NLP fields, achieving F1-scores of 0.883 for architectural issues and 0.894 for solutions. A user study further validated the quality (e.g., relevance and usefulness) of the identified ARPs and the extracted issue-solution pairs. Moreover, we applied ArchISMiner to three additional forums, releasing a dataset of over 18K architectural issue-solution pairs. Overall, ArchISMiner can help architects and developers identify ARPs and extract succinct, relevant, and useful architectural knowledge from developer communities more accurately and efficiently. The replication package of this study has been provided at https://github.com/JeanMusenga/ArchISPE

Designing institutions for social-ecological systems requires models that capture heterogeneity, uncertainty, and strategic interaction. Multiple modeling approaches have emerged to meet this challenge, including empirical game-theoretic analysis (EGTA), which merges ABM's scale and diversity with game-theoretic models' formal equilibrium analysis. The newly popular class of LLM-driven simulations provides yet another approach, and it is not clear how these approaches can be integrated with one another, nor whether the resulting simulations produce a plausible range of behaviours for real-world social-ecological governance. To address this gap, we compare four LLM-augmented frameworks: procedural ABMs, generative ABMs, LLM-EGTA, and expert guided LLM-EGTA, and evaluate them on a real-world case study of irrigation and fishing in the Amu Darya basin under centralized and decentralized governance. Our results show: first, procedural ABMs, generative ABMs, and LLM-augmented EGTA models produce strikingly different patterns of collective behaviour, highlighting the value of methodological diversity. Second, inducing behaviour through system prompts in LLMs is less effective than shaping behaviour through parameterized payoffs in an expert-guided EGTA-based model.

Masked diffusion models (MDMs) offer a compelling alternative to autoregressive models (ARMs) for discrete text generation because they enable parallel token sampling, rather than sequential, left-to-right generation. This means potentially much faster inference. However, effective parallel sampling faces two competing requirements: (i) simultaneously updated tokens must be conditionally independent, and (ii) updates should prioritise high-confidence predictions. These goals conflict because high-confidence predictions often cluster and depend on each other, opportunities for parallel updates. We present PUNT, a model-agnostic sampler that reconciles this trade-off. Our method identifies token dependencies and removes lower-confidence tokens from conflicting groups. This produces sets of indices for unmasking that satisfy both independence and confidence criteria. Our approach ensures improved parallel unmasking through approximate conditional independence testing. Our experiments show that PUNT delivers a superior trade-off between accuracy and compute when compared to other strong training-free baselines, especially for generation of longer sequences. On the IFEval benchmark, it achieves up to 16\% higher accuracy over baseline methods, including sequential generation (one-by-one). These gains hold across different values of hyperparameters, mitigating the need for brittle hyperparameter tuning. Moreover, we observe that PUNT induces an emergent hierarchical generation strategy, where the model first establishes high-level paragraph structure before local refinement, suggesting a planning-like generation process that contributes to strong alignment performance.

We show that large language models (LLMs) can be used to distinguish the writings of different authors. Specifically, an individual GPT-2 model, trained from scratch on the works of one author, will predict held-out text from that author more accurately than held-out text from other authors. We suggest that, in this way, a model trained on one author's works embodies the unique writing style of that author. We first demonstrate our approach on books written by eight different (known) authors. We also use this approach to confirm R. P. Thompson's authorship of the well-studied 15th book of the Oz series, originally attributed to F. L. Baum.

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$. Given the success of Transformers, improving their runtime during both training and inference is a popular research area. One such approach is the introduction of the linear attention (LA) mechanisms, which offers a linear time complexity of $O(ND^2)$ and have demonstrated comparable accuracy to regular attention. However, LA in practice lags behind its theoretical efficiency. We propose a novel method for LA's forward and backward passes, along with a highly-optimized CUDA implementation. Our approach outperforms the state-of-the-art by 3.3 times in speed and reduces memory consumption by 3.6 times. We validate these improvements in both single-layer and end-to-end settings by training a 1.4 billion parameter language model, which demonstrates similar expressivity to regular attention on major reasoning benchmarks.

Large Language Models (LLMs) are trained to support an increasing number of languages, yet their predefined tokenizers remain a bottleneck for adapting models to lower-resource or distinct-script languages. Existing tokenizer transfer methods typically rely on semantic heuristics to initialize new embeddings, ignoring higher-layer model dynamics and limiting transfer quality. We propose Model-A ware Tokenizer Transfer (MA TT), a method that incorporates model internals into the tokenizer transfer process. MA TT introduces an Attention Influence Modeling (AIM) objective that distills inter-token communication patterns from a source model into a target model with a new tokenizer, providing an efficient warm-up before standard language modeling. Unlike approaches that focus solely on embedding similarity, MA TT leverages attention behavior to guide embedding initialization and adaptation. Experiments across diverse linguistic settings show that MA TT recovers a large fraction of the original model's performance within a few GPU hours, outperforming heuristic baselines. These results demonstrate that incorporating model-level signals offers a practical and effective path toward robust tokenizer transfer in multilingual LLMs. Recent advances in large language models (LLMs) have shifted attention from training monolingual models (Jiang et al., 2023; Touvron et al., 2023) to covering an increasing number of languages (Grattafiori et al., 2024; Team et al., 2025).

The use of Large Language Models (LLMs) to support tasks in software development has steadily increased over recent years. From assisting developers in coding activities to providing conversational agents that answer newcomers' questions. In collaboration with the Mozilla Foundation, this study evaluates the effectiveness of Retrieval-Augmented Generation (RAG) in assisting developers within the Mozilla Firefox project. We conducted an empirical analysis comparing responses from human developers, a standard GPT model, and a GPT model enhanced with RAG, using real queries from Mozilla's developer chat rooms. To ensure a rigorous evaluation, Mozilla experts assessed the responses based on helpfulness, comprehensiveness, and conciseness. The results show that RAG-assisted responses were more comprehensive than human developers (62.50% to 54.17%) and almost as helpful (75.00% to 79.17%), suggesting RAG's potential to enhance developer assistance. However, the RAG responses were not as concise and often verbose. The results show the potential to apply RAG-based tools to Open Source Software (OSS) to minimize the load to core maintainers without losing answer quality. Toning down retrieval mechanisms and making responses even shorter in the future would enhance developer assistance in massive projects like Mozilla Firefox.

Evolutionary algorithms (EAs) have proven effective in exploring the vast solution spaces typical of graph-structured combinatorial problems. However, traditional encoding schemes, such as binary or numerical representations, often fail to straightforwardly capture the intricate structural properties of networks. Through employing the image-based encoding to preserve topological context, this study utilizes multimodal large language models (MLLMs) as evolutionary operators to facilitate structure-aware optimization over graph data. To address the visual clutter inherent in large-scale network visualizations, we leverage graph sparsification techniques to simplify structures while maintaining essential structural features. To further improve robustness and mitigate bias from different sparsification views, we propose a cooperative evolutionary optimization framework that facilitates cross-domain knowledge transfer and unifies multiple sparsified variants of diverse structures. Additionally, recognizing the sensitivity of MLLMs to network layout, we introduce an ensemble strategy that aggregates outputs from various layout configurations through consensus voting. Finally, experiments on real-world networks through various tasks demonstrate that our approach improves both the quality and reliability of solutions in MLLM-driven evolutionary optimization.

Software Engineering Agents (SWE-Agents) have proven effective for traditional software engineering tasks with accessible codebases, but their performance for embodied tasks requiring well-designed information discovery remains unexplored. We present the first extended evaluation of SWE-Agents on controller generation for embodied tasks, adapting Mini-SWE-Agent (MSWEA) to solve 20 diverse embodied tasks from the Minigrid environment. Our experiments compare agent performance across different information access conditions: with and without environment source code access, and with varying capabilities for interactive exploration. We quantify how different information access levels affect SWE-Agent performance for embodied tasks and analyze the relative importance of static code analysis versus dynamic exploration for task solving. This work establishes controller generation for embodied tasks as a crucial evaluation domain for SWE-Agents and provides baseline results for future research in efficient reasoning systems.

Automatic literature survey generation has attracted increasing attention, yet most existing systems follow a one-shot paradigm, where a large set of papers is retrieved at once and a static outline is generated before drafting. This design often leads to noisy retrieval, fragmented structures, and context overload, ultimately limiting survey quality. Inspired by the iterative reading process of human researchers, we propose \ours, a framework based on recurrent outline generation, in which a planning agent incrementally retrieves, reads, and updates the outline to ensure both exploration and coherence. To provide faithful paper-level grounding, we design paper cards that distill each paper into its contributions, methods, and findings, and introduce a review-and-refine loop with visualization enhancement to improve textual flow and integrate multimodal elements such as figures and tables. Experiments on both established and emerging topics show that \ours\ substantially outperforms state-of-the-art baselines in content coverage, structural coherence, and citation quality, while producing more accessible and better-organized surveys. To provide a more reliable assessment of such improvements, we further introduce Survey-Arena, a pairwise benchmark that complements absolute scoring and more clearly positions machine-generated surveys relative to human-written ones. The code is available at https://github.com/HancCui/IterSurvey\_Autosurveyv2.