Recently, we have witnessed the rapid development of large language models, which have demonstrated excellent capabilities in the downstream task of code generation. However, despite their potential, LLM-based code generation still faces numerous technical and evaluation challenges, particularly when embedded in real-world development. In this paper, we present our vision for current research directions, and provide an in-depth analysis of existing studies on this task. We propose a six-layer vision framework that categorizes code generation process into distinct phases, namely Input Phase, Orchestration Phase, Development Phase, and Validation Phase. Additionally, we outline our vision workflow, which reflects on the currently prevalent frameworks. We systematically analyse the challenges faced by large language models, including those LLM-based agent frameworks, in code generation tasks. With these, we offer various perspectives and actionable recommendations in this area. Our aim is to provide guidelines for improving the reliability, robustness and usability of LLM-based code generation systems. Ultimately, this work seeks to address persistent challenges and to provide practical suggestions for a more pragmatic LLM-based solution for future code generation endeavors.

We explore the ability of two LLMs -- GPT-4o and Claude Sonnet 3.5 -- to transcribe historical handwritten documents in a tabular format and compare their performance to traditional OCR/HTR systems: EasyOCR, Keras, Pytesseract, and TrOCR. Considering the tabular form of the data, two types of experiments are executed: one where the images are split line by line and the other where the entire scan is used as input. Based on CER and BLEU, we demonstrate that LLMs outperform the conventional OCR/HTR methods. Moreover, we also compare the evaluated CER and BLEU scores to human evaluations to better judge the outputs of whole-scan experiments and understand influential factors for CER and BLEU. Combining judgments from all the evaluation metrics, we conclude that two-shot GPT-4o for line-by-line images and two-shot Claude Sonnet 3.5 for whole-scan images yield the transcriptions of the historical records most similar to the ground truth.

The Neural Contextual Reinforcement Framework introduces an innovative approach to enhancing the logical coherence and structural consistency of text generated by large language models. Leveraging reinforcement learning principles, the framework integrates custom reward functions and dynamic context alignment mechanisms to address challenges inherent in maintaining long-range dependencies across extended sequences. The architecture incorporates multi-head attention layers and hierarchical encoding modules, enabling the model to produce outputs that align closely with human expectations of logical structure and semantic flow. Quantitative evaluations across diverse datasets demonstrate substantial improvements in coherence metrics, perplexity reduction, and semantic alignment, showcasing the framework's ability to outperform baseline models in both general and domain-specific tasks. Qualitative analyses further highlight the framework's capacity to generate text with improved narrative clarity and reduced redundancy, reflecting its effectiveness in balancing fluency with structural precision. In addition to its performance gains, the framework exhibits robustness in handling noisy input data and scalability across varying model sizes, reinforcing its versatility in practical applications. Experimental results reveal that optimal context window sizes significantly influence coherence outcomes, showing the importance of architectural flexibility in adapting to diverse linguistic structures. Cross-lingual performance evaluations affirm the framework's adaptability to multiple languages, extending its utility beyond monolingual contexts. Resource efficiency analyses indicate a reduction in computational overhead compared to traditional approaches, emphasizing the practicality of the framework for large-scale deployment.

The 3rd Generation Partnership Project (3GPP) documents is key standards in global telecommunications, while posing significant challenges for engineers and researchers in the telecommunications field due to the large volume and complexity of their contents as well as the frequent updates. Large language models (LLMs) have shown promise in natural language processing tasks, but their general-purpose nature limits their effectiveness in specific domains like telecommunications. To address this, we propose Chat3GPP, an open-source retrieval-augmented generation (RAG) framework tailored for 3GPP specifications. By combining chunking strategies, hybrid retrieval and efficient indexing methods, Chat3GPP can efficiently retrieve relevant information and generate accurate responses to user queries without requiring domain-specific fine-tuning, which is both flexible and scalable, offering significant potential for adapting to other technical standards beyond 3GPP. We evaluate Chat3GPP on two telecom-specific datasets and demonstrate its superior performance compared to existing methods, showcasing its potential for downstream tasks like protocol generation and code automation.

--Foundation models are rapidly improving the capability of robots in performing everyday tasks autonomously such as meal preparation, yet robots will still need to be instructed by humans due to model performance, the difficulty of capturing user preferences, and the need for user agency. Robots can be instructed using various methods--natural language conveys immediate instructions but can be abstract or ambiguous, whereas end-user programming supports longer-horizon tasks but interfaces face difficulties in capturing user intent. In this work, we propose using direct manipulation of images as an alternative paradigm to instruct robots, and introduce a specific instantiation called ImageInThat which allows users to perform direct manipulation on images in a timeline-style interface to generate robot instructions. Through a user study, we demonstrate the efficacy of ImageInThat to instruct robots in kitchen manipulation tasks, comparing it to a text-based natural language instruction method. The results show that participants were faster with ImageInThat and preferred to use it over the text-based method. Supplementary material including code can be found at: https://image-in-that.github.io/. Advances in foundation models are rapidly improving the capabilities of autonomous robots, bringing us closer to robots entering our homes where they can complete everyday tasks. However, the need for human instructions will persist-- whether due to limitations in robot policies, models trained on internet-scale data that may not capture the specifics of users' environments or preferences, or simply the desire for users to maintain control over their robots' actions. For instance, a robot asked to wash dishes might follow a standard cleaning routine--e.g., by placing everything in the dishwasher and then putting them away in the cupboard--but may not respect a user's preferences-- e.g., needing to wash delicate glasses "by hand" or organizing cleaned dishes in a specific way--thus necessitating human intervention. We introduce a new paradigm for instructing robots through the direct manipulation of images. ImageInThat is a specific instantiation of this paradigm where users can manipulate images in a timeline-style interface to create instructions for the robot to execute. Existing methods for instructing robots range from those that focus on commanding the robot for the purpose of immediate execution ( e.g., uttering a language instruction to wash glasses by hand [1]) to methods that program the robot such as learning from demonstration [2] or end-user robot programming [3]. However, prior methods, whether they are used for commanding or programming, have notable drawbacks.

The integration of AI in education offers significant potential to enhance learning efficiency. Large Language Models (LLMs), such as ChatGPT, Gemini, and Llama, allow students to query a wide range of topics, providing unprecedented flexibility. However, LLMs face challenges, such as handling varying content relevance and lack of personalization. To address these challenges, we propose TutorLLM, a personalized learning recommender LLM system based on Knowledge Tracing (KT) and Retrieval-Augmented Generation (RAG). The novelty of TutorLLM lies in its unique combination of KT and RAG techniques with LLMs, which enables dynamic retrieval of context-specific knowledge and provides personalized learning recommendations based on the student's personal learning state. Specifically, this integration allows TutorLLM to tailor responses based on individual learning states predicted by the Multi-Features with Latent Relations BERT-based KT (MLFBK) model and to enhance response accuracy with a Scraper model. The evaluation includes user assessment questionnaires and performance metrics, demonstrating a 10\% improvement in user satisfaction and a 5\% increase in quiz scores compared to using general LLMs alone.

Tokenization is a fundamental step in natural language processing, breaking text into units that computational models can process. While learned subword tokenizers have become the de-facto standard, they present challenges such as large vocabularies, limited adaptability to new domains or languages, and sensitivity to spelling errors and variations. To overcome these limitations, we investigate a hierarchical architecture for autoregressive language modelling that combines character-level and word-level processing. It employs a lightweight character-level encoder to convert character sequences into word embeddings, which are then processed by a word-level backbone model and decoded back into characters via a compact character-level decoder. This method retains the sequence compression benefits of word-level tokenization without relying on a rigid, predefined vocabulary. We demonstrate, at scales up to 7 billion parameters, that hierarchical transformers match the downstream task performance of subword-tokenizer-based models while exhibiting significantly greater robustness to input perturbations. Additionally, during continued pretraining on an out-of-domain language, our model trains almost twice as fast, achieves superior performance on the target language, and retains more of its previously learned knowledge. Hierarchical transformers pave the way for NLP systems that are more robust, flexible, and generalizable across languages and domains.

Geocoding involves automatic extraction of location coordinates of incidents reported in news articles, and can be used for epidemic intelligence or disaster management. This paper introduces Retrieval-Augmented Coordinate Capture Of Online News articles (RACCOON), an open-source geocoding approach that extracts geolocations from news articles. RACCOON uses a retrieval-augmented generation (RAG) approach where candidate locations and associated information are retrieved in the form of context from a location database, and a prompt containing the retrieved context, location mentions and news articles is fed to an LLM to generate the location coordinates. Our evaluation on three datasets, two underlying LLMs, three baselines and several ablation tests based on the components of RACCOON demonstrate the utility of RACCOON. To the best of our knowledge, RACCOON is the first RAG-based approach for geocoding using pre-trained LLMs.

In computational social science (CSS), researchers analyze documents to explain social and political phenomena. In most scenarios, CSS researchers first obtain labels for documents and then explain labels using interpretable regression analyses in the second step. One increasingly common way to annotate documents cheaply at scale is through large language models (LLMs). However, like other scalable ways of producing annotations, such surrogate labels are often imperfect and biased. We present a new algorithm for using imperfect annotation surrogates for downstream statistical analyses while guaranteeing statistical properties--like asymptotic unbiasedness and proper uncertainty quantification--which are fundamental to CSS research.

Procedural activity understanding requires perceiving human actions in terms of a broader task, where multiple keysteps are performed in sequence across a long video to reach a final goal state---such as the steps of a recipe or the steps of a DIY fix-it task. Prior work largely treats keystep recognition in isolation of this broader structure, or else rigidly confines keysteps to align with a particular sequential script. We propose discovering a task graph automatically from how-to videos to represent probabilistically how people tend to execute keysteps, then leverage this graph to regularize keystep recognition in novel videos. On multiple datasets of real-world instructional video, we show the impact: more reliable zero-shot keystep localization and improved video representation learning, exceeding the state of the art.