Abstract--The use of AI code-generation tools is becoming increasingly common, making it important to understand how software developers are adopting these tools. In this study, we investigate how developers engage with Amazon's Code-Whisperer, an LLM-based code-generation tool. We conducted two user studies with two groups of 10 participants each, interacting with CodeWhisperer - the first to understand which interactions were critical to capture and the second to collect low-level interaction data using a custom telemetry plugin. Our mixed-methods analysis identified four behavioral patterns: 1) incremental code refinement, 2) explicit instruction using natural language comments, 3) baseline structuring with model suggestions, and 4) integrative use with external sources. We provide a comprehensive analysis of these patterns . Several IDE-based code generation tools have been released in the past few years, such as GitHub's Copilot [8], Kite [14], Amazon's Code Whisperer [20], Tabnine [22], and WPCode [28]. Research reveals that being able to achieve their full potential requires a certain level of guidance to ensure that the tool's output aligns with the user's goal [21].

Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that can reason about and simulate student errors are useful for providing real-time feedback in the classroom or offline practice for educators-in-training. This paper presents a new method, MISTAKE, that (1) constructs high-quality synthetic examples of reasoning errors by leveraging cycle consistency between incorrect answers and latent misconceptions; and (2) uses the generated data to learn models for student simulation, misconception classification, and answer generation. We evaluate MISTAKE on three educational tasks and find that it results in (1) higher accuracy when simulating incorrect student answers based on specific misconceptions, (2) increased performance inferring latent misconceptions from observed incorrect answers, and (3) higher alignment with expert-written distractor answers when generating incorrect answers (e.g., for multiple-choice tests).

Abstract--Traditional named entity recognition (NER) aims to identify text mentions into pre-defined entity types. Continual Named Entity Recognition (CNER) is introduced since entity categories are continuously increasing in various real-world scenarios. In this paper, we propose GenCNER, a simple but effective Generative framework for CNER to mitigate the above drawbacks. Specifically, we skillfully convert the CNER task into sustained entity triplet sequence generation problem and utilize a powerful pre-trained seq2seq model to solve it. Additionally, we design a type-specific confidence-based pseudo labeling strategy along with knowledge distillation (KD) to preserve learned knowledge and alleviate the impact of label noise at the triplet level. Experimental results on two benchmark datasets show that our framework outperforms previous state-of-the-art methods in multiple CNER settings, and achieves the smallest gap compared with non-CL results. I. Introduction Named Entity Recognition (NER) is one fundamental task in NLP fields due to its wide application in entity linking [1], relation extraction [2] and knowledge graph [3].

This paper presents an AI-driven IoT robotic teleoperation system designed for real-time remote manipulation and intelligent visual monitoring, tailored for smart city applications. The architecture integrates a Flutter-based cross-platform mobile interface with MQTT-based control signaling and WebRTC video streaming via the LiveKit framework. A YOLOv11-nano model is deployed for lightweight object detection, enabling real-time perception with annotated visual overlays delivered to the user interface. Control commands are transmitted via MQTT to an ESP8266-based actuator node, which coordinates multi-axis robotic arm motion through an Arduino Mega2560 controller. The backend infrastructure is hosted on DigitalOcean, ensuring scalable cloud orchestration and stable global communication. Latency evaluations conducted under both local and international VPN scenarios (including Hong Kong, Japan, and Belgium) demonstrate actuator response times as low as 0.2 seconds and total video latency under 1.2 seconds, even across high-latency networks. This low-latency dual-protocol design ensures responsive closed-loop interaction and robust performance in distributed environments. Unlike conventional teleoperation platforms, the proposed system emphasizes modular deployment, real-time AI sensing, and adaptable communication strategies, making it well-suited for smart city scenarios such as remote infrastructure inspection, public equipment servicing, and urban automation. Future enhancements will focus on edge-device deployment, adaptive routing, and integration with city-scale IoT networks to enhance resilience and scalability.

Truly reliable AI requires more than simply scaling up knowledge; it demands the ability to know what it knows and when it does not. Yet recent research shows that even the best LLMs misjudge their own competence in more than one in five cases, making any response born of such internal uncertainty impossible to fully trust. Inspired by self-improvement reinforcement learning techniques that require minimal data, we present a simple but powerful framework KnowRL that strengthens a model's internal understanding of its own feasibility boundaries, enabling safer and more responsible behaviour. Our framework combines two components: (i) introspection, where the model generates and classifies tasks it judges feasible or infeasible, and (ii) consensus-based rewarding, where stability of self-knowledge assessment is reinforced through internal agreement. By using internally generated data, this design strengthens consistency in self-knowledge and entirely avoids costly external supervision. In experiments on LLaMA-3.1-8B and Qwen-2.5-7B, KnowRL steadily improved self-knowledge, validated by both intrinsic self-consistency and extrinsic benchmarking. With nothing more than a small seed set and no external supervision, our method drove gains as high as 28% in accuracy and 12% in F1, outperforming baselines in just a few iterations. Our framework essentially unlocks the untapped capacity of LLMs to self-improve their knowledge awareness, opening the door to reliable, more accountable AI and safer deployment in critical applications. Owing to its simplicity and independence from external effort, we encourage applying this reliability-enhancing process to all future models.

This paper investigates automated skill decomposition using Large Language Models (LLMs) and proposes a rigorous, ontology-grounded evaluation framework. Our framework standardizes the pipeline from prompting and generation to normalization and alignment with ontology nodes. To evaluate outputs, we introduce two metrics: a semantic F1-score that uses optimal embedding-based matching to assess content accuracy, and a hierarchy-aware F1-score that credits structurally correct placements to assess granularity. We conduct experiments on ROME-ESCO-DecompSkill, a curated subset of parents, comparing two prompting strategies: zero-shot and leakage-safe few-shot with exemplars. Across diverse LLMs, zero-shot offers a strong baseline, while few-shot consistently stabilizes phrasing and granularity and improves hierarchy-aware alignment. A latency analysis further shows that exemplar-guided prompts are competitive - and sometimes faster - than unguided zero-shot due to more schema-compliant completions. Together, the framework, benchmark, and metrics provide a reproducible foundation for developing ontology-faithful skill decomposition systems.

Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating errors and inefficiencies. While reinforcement learning offers one alternative, the associated exploration typically results in sacrificing data efficiency. This work explores how agents trained with imitation learning can learn robust representations from both optimal and suboptimal demonstrations when given access to constructive language feedback as a means to contextualise different modes of behaviour. We directly provide language feedback embeddings as part of the input sequence into a Transformer-based policy, and optionally complement the traditional next action prediction objective with auxiliary self-supervised learning objectives for feedback prediction. We test our approach on a range of embodied Vision-and-Language tasks in our custom BabyAI-XGen environment and show significant improvements in agents' compositional generalisation abilities and robustness, suggesting that our data-efficient method allows models to successfully convert suboptimal behaviour into learning opportunities. Overall, our results suggest that language feedback is a competitive and intuitive alternative to intermediate scalar rewards for language-specified embodied tasks.

Large language models (LLMs) based Agents are increasingly pivotal in simulating and understanding complex human systems and interactions. We propose the AI-Agent School (AAS) system, built around a self-evolving mechanism that leverages agents for simulating complex educational dynamics. Addressing the fragmented issues in teaching process modeling and the limitations of agents performance in simulating diverse educational participants, AAS constructs the Zero-Exp strategy, employs a continuous "experience-reflection-optimization" cycle, grounded in a dual memory base comprising experience and knowledge bases and incorporating short-term and long-term memory components. Through this mechanism, agents autonomously evolve via situated interactions within diverse simulated school scenarios. This evolution enables agents to more accurately model the nuanced, multi-faceted teacher-student engagements and underlying learning processes found in physical schools. Experiment confirms that AAS can effectively simulate intricate educational dynamics and is effective in fostering advanced agent cognitive abilities, providing a foundational stepping stone from the "Era of Experience" to the "Era of Simulation" by generating high-fidelity behavioral and interaction data.

Sign languages serve as essential communication systems for individuals with hearing and speech impairments. However, digital linguistic dataset resources for underrepresented sign languages, such as Nepali Sign Language (NSL), remain scarce. This study introduces the first benchmark dataset for NSL, consisting of 36 gesture classes with 1,500 samples per class, designed to capture the structural and visual features of the language. To evaluate recognition performance, we fine-tuned MobileNetV2 and ResNet50 architectures on the dataset, achieving classification accuracies of 90.45% and 88.78%, respectively. These findings demonstrate the effectiveness of convolutional neural networks in sign recognition tasks, particularly within low-resource settings. To the best of our knowledge, this work represents the first systematic effort to construct a benchmark dataset and assess deep learning approaches for NSL recognition, highlighting the potential of transfer learning and fine-tuning for advancing research in underexplored sign languages.

Deciphering the function of unseen protein sequences is a fundamental challenge with broad scientific impact, yet most existing methods depend on task-specific adapters or large-scale supervised fine-tuning. We introduce the "Protein-as-Second-Language" framework, which reformulates amino-acid sequences as sentences in a novel symbolic language that large language models can interpret through contextual exemplars. Our approach adaptively constructs sequence-question-answer triples that reveal functional cues in a zero-shot setting, without any further training. To support this process, we curate a bilingual corpus of 79,926 protein-QA instances spanning attribute prediction, descriptive understanding, and extended reasoning. Empirically, our method delivers consistent gains across diverse open-source LLMs and GPT-4, achieving up to 17.2% ROUGE-L improvement (average +7%) and even surpassing fine-tuned protein-specific language models. These results highlight that generic LLMs, when guided with protein-as-language cues, can outperform domain-specialized models, offering a scalable pathway for protein understanding in foundation models.