Developers often evolve an existing software system by making internal changes, called migration. Moving to a new framework, changing implementation to improve efficiency, and upgrading a dependency to its latest version are examples of migrations. Migration is a common and typically continuous maintenance task undertaken either manually or through tooling. Certain migrations are labor intensive and costly, developers do not find the required work rewarding, and they may take years to complete. Hence, automation is preferred for such migrations. In this paper, we discuss a large-scale, costly and traditionally manual migration project at Google, propose a novel automated algorithm that uses change location discovery and a Large Language Model (LLM) to aid developers conduct the migration, report the results of a large case study, and discuss lessons learned. Our case study on 39 distinct migrations undertaken by three developers over twelve months shows that a total of 595 code changes with 93,574 edits have been submitted, where 74.45% of the code changes and 69.46% of the edits were generated by the LLM. The developers reported high satisfaction with the automated tooling, and estimated a 50% reduction on the total time spent on the migration compared to earlier manual migrations. Our results suggest that our automated, LLM-assisted workflow can serve as a model for similar initiatives.

--This paper introduces a novel framework for designing efficient neural network architectures specifically tailored to tiny machine learning (TinyML) platforms. The LLM-guided search explores a hierarchical search space, refining candidate architectures through Pareto optimization based on accuracy, multiply-accumulate operations (MACs), and memory metrics. The best-performing architectures are further fine-tuned using logits-based KD with a pre-trained ViT-B/16 model, which enhances generalization without increasing model size. Evaluated on the CIF AR-100 dataset and deployed on an STM32H7 microcontroller (MCU), the three proposed models, LMaNet-Elite, LMaNet-Core, and QwNet-Core, achieve accuracy scores of 74.50%, 74.20% and 73.00%, respectively. All three models surpass current state-of-the-art (SOT A) models, such as MCUNet-in3/in4 (69.62% / 72.86%) and XiNet (72.27%), while maintaining a low computational cost of less than 100 million MACs and adhering to the stringent 320 KB static random-access memory (SRAM) constraint. These results demonstrate the efficiency and performance of the proposed framework for TinyML platforms, underscoring the potential of combining LLM-driven search, Pareto optimization, KD, and explainability to develop accurate, efficient, and interpretable models. This approach opens new possibilities in NAS, enabling the design of efficient architectures specifically suited for TinyML. T o facilitate further research and development in this field, the proposed framework and the best-performing architectures are made publicly available at Link. The proliferation of internet of things (IoT) devices built on tiny hardware platforms, such as microcontrollers (MCUs), has underscored the demand for deploying deep learning (DL) models in resource-constrained environments [1]. Despite their potential to democratize artificial intelligence (AI), these devices face unique challenges that differ significantly from mobile DL, particularly due to stringent memory limitations. For instance, the typical MCU has a static random-access memory (SRAM) of less than 512kB, which poses a substantial obstacle for running conventional DL models [2]. Numerous lightweight deep neural network (DNN) architectures, such as MobileNet [3], have demonstrated the utility of handcrafted model design for mobile applications. Y et, when adapted for MCUs, the limited memory resources pose significant hurdles. Our proposed architectures balance accuracy and efficiency, reducing model size and computational cost compared to baselines.

Despite dramatic recent progress in NLP, it is still a major challenge to apply Large Language Models (LLM) to low-resource languages. This is made visible in benchmarks such as Cross-Lingual Natural Language Inference (XNLI), a key task that demonstrates cross-lingual capabilities of NLP systems across a set of 15 languages. In this paper, we extend the XNLI task for one additional low-resource language, Myanmar, as a proxy challenge for broader low-resource languages, and make three core contributions. First, we build a dataset called Myanmar XNLI (myXNLI) using community crowd-sourced methods, as an extension to the existing XNLI corpus. This involves a two-stage process of community-based construction followed by expert verification; through an analysis, we demonstrate and quantify the value of the expert verification stage in the context of community-based construction for low-resource languages. We make the myXNLI dataset available to the community for future research. Second, we carry out evaluations of recent multilingual language models on the myXNLI benchmark, as well as explore data-augmentation methods to improve model performance. Our data-augmentation methods improve model accuracy by up to 2 percentage points for Myanmar, while uplifting other languages at the same time. Third, we investigate how well these data-augmentation methods generalise to other low-resource languages in the XNLI dataset.

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code generation, even minor errors can easily break the entire solution. Leveraging multiple sampled solutions can significantly improve the overall output quality. One effective way to enhance code generation is by pairing a code generation model with a reranker model, which selects the best solution from the generated samples. We propose a novel iterative self-training approach for self-training reranker models using Proximal Policy Optimization (PPO), aimed at improving both reranking accuracy and the overall code generation process. Unlike traditional PPO approaches, where the focus is on optimizing a generative model with a reward model, our approach emphasizes the development of a robust reward/reranking model. This model improves the quality of generated code through reranking and addresses problems and errors that the reward model might overlook during PPO alignment with the reranker. Our method iteratively refines the training dataset by re-evaluating outputs, identifying high-scoring negative examples, and incorporating them into the training loop, that boosting model performance. Our evaluation on the MultiPL-E dataset demonstrates that our 13.4B parameter model outperforms a 33B model in code generation quality while being three times faster. Moreover, it achieves performance comparable to GPT-4 and surpasses it in one programming language.

A significant trend in enhancing the capabilities of these models is test-time scaling (Yang et al., 2025; Wu et al., 2025), where increasing computational resources allocated during inference leads to notable performance improvements. Models such as OpenAI's o1 series (OpenAI, 2024) and DeepSeek-R1 (DeepSeek-AI, 2025) have demonstrated the effectiveness of this approach across various tasks and benchmarks (Lightman et al., 2023; Huang et al., 2024). The capability of these models to achieve superior results by allocating additional computational resources during inference indicates an important shift in optimizing performance for LLMs. Specifically, dedicating more computation to the answer-generation process, rather than solely relying on scaling training data and model parameters, can lead to significant improvements, particularly in tasks that require complex reasoning (Snell et al., 2024). The success of test-time scaling thus emphasizes the crucial role of computation during the answer-generation phase.

To develop effective sequential recommender systems, numerous methods have been proposed to model historical user behaviors. Despite the effectiveness, these methods share the same fast thinking paradigm. That is, for making recommendations, these methods typically encodes user historical interactions to obtain user representations and directly match these representations with candidate item representations. However, due to the limited capacity of traditional lightweight recommendation models, this one-step inference paradigm often leads to suboptimal performance. To tackle this issue, we present a novel slow thinking recommendation model, named STREAM-Rec. Our approach is capable of analyzing historical user behavior, generating a multi-step, deliberative reasoning process, and ultimately delivering personalized recommendations. In particular, we focus on two key challenges: (1) identifying the suitable reasoning patterns in recommender systems, and (2) exploring how to effectively stimulate the reasoning capabilities of traditional recommenders. To this end, we introduce a three-stage training framework. In the first stage, the model is pretrained on large-scale user behavior data to learn behavior patterns and capture long-range dependencies. In the second stage, we design an iterative inference algorithm to annotate suitable reasoning traces by progressively refining the model predictions. This annotated data is then used to fine-tune the model. Finally, in the third stage, we apply reinforcement learning to further enhance the model generalization ability. Extensive experiments validate the effectiveness of our proposed method.

Recent breakthroughs in large Language Models (LLMs) have enabled various generative tasks on a single model. Real-world services (e.g., OpenAI's ChatGPT [27]) powered by an LLM often concurrently support latency-critical requests for interactive applications (e.g., question-answering systems, referred to as real-time or RT requests) and throughput-oriented requests for back-of-house processing (e.g., documents batch processing [28], referred to best-effort or BE requests), with complex hybrid inference workloads to the underlying model. State-of-the-art (SOTA) LLM serving systems dedicate machines to each type of request, towards either low inference latency or high serving throughput, respectively. This practice simplifies request scheduling and management but suffers from poor resource utilization. We propose BROS, a hybrid LLM serving system that aims to collocate RT/BE requests, meeting RT requests' latency requirements while maintaining BE requests' throughput. BROS formulates the problem of hybrid RT/BE request scheduling and solves it with a dynamic priority-based algorithm. BROS designs a bidirectional KV cache management mechanism, allowing RT requests to share KV memory with BE requests to remove the scheduling restrictions caused by insufficient KV memory and improve utilization. Extensive experiments validate that BROS achieves a good trade-off when serving hybrid RT and BE requests. It significantly reduces the latency of RT requests (up to 74.20%), improving their fine-grained service level objectives (SLOs) attainments (up to 36.38x), with negligible throughput reduction for BE requests, showing significant advantages over SOTA systems like vLLM and TGI.

Recent years have witnessed significant progress in large language models' (LLMs) reasoning, which is largely due to the chain-of-thought (CoT) approaches, allowing models to generate intermediate reasoning steps before reaching the final answer. Building on these advances, state-of-the-art LLMs are instruction-tuned to provide long and detailed CoT pathways when responding to reasoning-related questions. However, human beings are naturally cognitive misers and will prompt language models to give rather short responses, thus raising a significant conflict with CoT reasoning. In this paper, we delve into how LLMs' reasoning performance changes when users provide short-path prompts. The results and analysis reveal that language models can reason effectively and robustly without explicit CoT prompts, while under short-path prompting, LLMs' reasoning ability drops significantly and becomes unstable, even on grade-school problems. To address this issue, we propose two approaches: an instruction-guided approach and a fine-tuning approach, both designed to effectively manage the conflict. Experimental results show that both methods achieve high accuracy, providing insights into the trade-off between instruction adherence and reasoning accuracy in current models.

AirVista-II: An Agentic System for Embodied UA Vs T oward Dynamic Scene Semantic Understanding Fei Lin 1, Y onglin Tian 2, Tengchao Zhang 1, Jun Huang 1, Sangtian Guan 1, and Fei-Y ue Wang 2, 1 Abstract -- Unmanned Aerial V ehicles (UA Vs) are increasingly important in dynamic environments such as logistics transportation and disaster response. However, current tasks often rely on human operators to monitor aerial videos and make operational decisions. This mode of human-machine collaboration suffers from significant limitations in efficiency and adaptability. In this paper, we present AirVista-II--an end-to-end agentic system for embodied UA Vs, designed to enable general-purpose semantic understanding and reasoning in dynamic scenes. The system integrates agent-based task identification and scheduling, multimodal perception mechanisms, and differentiated keyframe extraction strategies tailored for various temporal scenarios, enabling the efficient capture of critical scene information. Experimental results demonstrate that the proposed system achieves high-quality semantic understanding across diverse UA V-based dynamic scenarios under a zero-shot setting.

Knowledge discovery is hindered by the increasing volume of publications and the scarcity of extensive annotated data. To tackle the challenge of information overload, it is essential to employ automated methods for knowledge extraction and processing. Finding the right balance between the level of supervision and the effectiveness of models poses a significant challenge. While supervised techniques generally result in better performance, they have the major drawback of demanding labeled data. This requirement is labor-intensive and time-consuming and hinders scalability when exploring new domains. In this context, our study addresses the challenge of identifying semantic relationships between biomedical entities (e.g., diseases, proteins) in unstructured text while minimizing dependency on supervision. We introduce a suite of unsupervised algorithms based on dependency trees and attention mechanisms and employ a range of pointwise binary classification methods. Transitioning from weakly supervised to fully unsupervised settings, we assess the methods' ability to learn from data with noisy labels. The evaluation on biomedical benchmark datasets explores the effectiveness of the methods. Our approach tackles a central issue in knowledge discovery: balancing performance with minimal supervision. By gradually decreasing supervision, we assess the robustness of pointwise binary classification techniques in handling noisy labels, revealing their capability to shift from weakly supervised to entirely unsupervised scenarios. Comprehensive benchmarking offers insights into the effectiveness of these techniques, suggesting an encouraging direction toward adaptable knowledge discovery systems, representing progress in creating data-efficient methodologies for extracting useful insights when annotated data is limited.