Autonomous mobile app interaction has become increasingly important with growing complexity of mobile applications. Developing intelligent agents that can effectively navigate and interact with mobile apps remains a significant challenge. In this paper, we propose an Explainable Behavior Cloning LLM Agent (EBC-LLMAgent), a novel approach that combines large language models (LLMs) with behavior cloning by learning demonstrations to create intelligent and explainable agents for autonomous mobile app interaction. EBC-LLMAgent consists of three core modules: Demonstration Encoding, Code Generation, and UI Mapping, which work synergistically to capture user demonstrations, generate executable codes, and establish accurate correspondence between code and UI elements. We introduce the Behavior Cloning Chain Fusion technique to enhance the generalization capabilities of the agent. Extensive experiments on five popular mobile applications from diverse domains demonstrate the superior performance of EBC-LLMAgent, achieving high success rates in task completion, efficient generalization to unseen scenarios, and the generation of meaningful explanations.
How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evaluation. The former hurts the fairness of benchmarks, and the latter hinders practitioners from selecting superior LLMs for specific programming domains. To address these two limitations, we propose a new benchmark - EvoCodeBench, which has the following advances: (1) Evolving data. EvoCodeBench will be dynamically updated every period (e.g., 6 months) to avoid data leakage. This paper releases the first version - EvoCodeBench-2403, containing 275 samples from 25 repositories. (2) A domain taxonomy and domain labels. Based on the statistics of open-source communities, we design a programming domain taxonomy consisting of 10 popular domains. Based on the taxonomy, we annotate each sample in EvoCodeBench with a domain label. (3) Domain-specific evaluations. Besides the Pass@k, we compute the Domain-Specific Improvement (DSI) and define LLMs' comfort and strange domains. These evaluations help practitioners select superior LLMs in specific domains and discover the shortcomings of existing LLMs. We evaluate 8 popular LLMs (e.g., gpt-4, DeepSeek Coder) on EvoCodeBench and summarize some insights. EvoCodeBench reveals the actual abilities of these LLMs in real-world repositories. For example, the highest Pass@1 of gpt-4 on EvoCodeBench-2403 is only 20.74%. Besides, we evaluate LLMs in different domains and discover their comfort and strange domains. For example, gpt-4 performs best in most domains but falls behind others in the Internet domain. StarCoder 2-15B unexpectedly performs well in the Database domain and even outperforms 33B LLMs. EvoCodeBench has been released.
Sampling is a basic operation in many inference-time algorithms of large language models (LLMs). To scale up inference efficiently with a limited compute, it is crucial to find an optimal allocation for sample compute budgets: Which sampling configurations (model, temperature, language, etc.) do we use? How many samples do we generate in each configuration? We formulate these choices as a learning problem and propose OSCA, an algorithm that Optimizes Sample Compute Allocation by finding an optimal mix of different inference configurations. Our experiments show that with our learned mixed allocation, we can achieve accuracy better than the best single configuration with 128x less compute on code generation and 25x less compute on 4 reasoning tasks. OSCA is also shown to be effective in agentic workflows beyond single-turn tasks, achieving a better accuracy on SWE-Bench with 3x less compute than the default configuration. Our code and generations are released at https://github.com/LeiLiLab/OSCA.
Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have emerged to evaluate the capabilities of large language models (LLMs) beyond standalone benchmarks like HumanEval and MBPP. Thus, a natural question is, would LLMs have similar performance in real world coding tasks as their performance in these benchmarks? Unfortunately, one cannot answer this question, since these benchmarks consist of short completions, synthetic examples, or focus on limited scale repositories, failing to represent real-world coding tasks. To address these challenges, we create REPOCOD, a Python code-generation benchmark containing complex tasks with realistic dependencies in real-world large projects and appropriate metrics for evaluating source code. It includes 980 whole-function generation tasks from 11 popular projects, 50.8% of which require repository-level context. REPOCOD includes 314 developer-written test cases per instance for better evaluation. We evaluate ten LLMs on REPOCOD and find that none achieves more than 30% pass@1 on REPOCOD, indicating the necessity of building stronger LLMs that can help developers in real-world software development. In addition, we found that retrieval-augmented generation achieves better results than using target function dependencies as context.
Recently, large language models (LLMs) have achieved significant progress in automated code generation. Despite their strong instruction-following capabilities, these models frequently struggled to align with user intent in coding scenarios. In particular, they were hampered by datasets that lacked diversity and failed to address specialized tasks or edge cases. Furthermore, challenges in supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) led to failures in generating precise, human-intent-aligned code. To tackle these challenges and improve the code generation performance for automated programming systems, we propose Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization (i.e., FALCON). FALCON is structured into two hierarchical levels. From the global level, long-term memory improves code quality by retaining and applying learned knowledge. At the local level, short-term memory allows for the incorporation of immediate feedback from compilers and AI systems. Additionally, we introduce meta-reinforcement learning with feedback rewards to solve the global-local bi-level optimization problem and enhance the model's adaptability across diverse code generation tasks. Extensive experiments demonstrate that our technique achieves state-of-the-art performance, leading other reinforcement learning methods by more than 4.5 percentage points on the MBPP benchmark and 6.1 percentage points on the Humaneval benchmark. The open-sourced code is publicly available at https://github.com/titurte/FALCON.
In the past few years, Large Language Models (LLMs) have exploded in usefulness and popularity for code generation tasks. However, LLMs still struggle with accuracy and are unsuitable for high-risk applications without additional oversight and verification. In particular, they perform poorly at generating code for highly complex systems, especially with unusual or out-of-sample logic. For such systems, verifying the code generated by the LLM may take longer than writing it by hand. We introduce a solution that divides the code generation into two parts; one to be handled by an LLM and one to be handled by formal methods-based program synthesis. We develop a benchmark to test our solution and show that our method allows the pipeline to solve problems previously intractable for LLM code generation.
Although LLMs are increasing the productivity of professional programmers, existing work shows that beginners struggle to prompt LLMs to solve text-to-code tasks. Why is this the case? This paper explores two competing hypotheses about the cause of student-LLM miscommunication: (1) students simply lack the technical vocabulary needed to write good prompts, and (2) students do not understand the extent of information that LLMs need to solve code generation tasks. We study (1) with a causal intervention experiment on technical vocabulary and (2) by analyzing graphs that abstract how students edit prompts and the different failures that they encounter. We find that substance beats style: a poor grasp of technical vocabulary is merely correlated with prompt failure; that the information content of prompts predicts success; that students get stuck making trivial edits; and more. Our findings have implications for the use of LLMs in programming education, and for efforts to make computing more accessible with LLMs.
Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to generate one token at a time, which can result in noticeable latency. Recent advances have indicated that search and repeated sampling can enhance performance in various applications, such as theorem proving, code generation, and alignment, by utilizing greater computational resources during inference. In this study, we demonstrate that diffusion language models are capable of generating at least 32 tokens simultaneously, while exceeding the performance of AR models in text quality and on the LAMBADA natural language understanding benchmark. This outcome is achieved through a novel distillation method for discrete diffusion models, which reduces the number of inference steps by a factor of 32-64. Practically, our models, even without caching, can generate tokens at a rate that is up to 8 times faster than AR models employing KV caching, and we anticipate further improvements with the inclusion of caching. Moreover, we demonstrate the efficacy of our approach for diffusion language models with up to 860M parameters.
Large Language Models (LLMs) have shown great potential in automating code generation; however, their ability to generate accurate circuit-level SPICE code remains limited due to a lack of hardware-specific knowledge. In this paper, we analyze and identify the typical limitations of existing LLMs in SPICE code generation. To address these limitations, we present SPICEPilot a novel Python-based dataset generated using PySpice, along with its accompanying framework. This marks a significant step forward in automating SPICE code generation across various circuit configurations. Our framework automates the creation of SPICE simulation scripts, introduces standardized benchmarking metrics to evaluate LLM's ability for circuit generation, and outlines a roadmap for integrating LLMs into the hardware design process. SPICEPilot is open-sourced under the permissive MIT license at https://github.com/ACADLab/SPICEPilot.git.
The rise of spatiotemporal data and the need for efficient geospatial modeling have spurred interest in automating these tasks with large language models (LLMs). However, general LLMs often generate errors in geospatial code due to a lack of domain-specific knowledge on functions and operators. To address this, a retrieval-augmented generation (RAG) approach, utilizing an external knowledge base of geospatial functions and operators, is proposed. This study introduces a framework to construct such a knowledge base, leveraging geospatial script semantics. The framework includes: Function Semantic Framework Construction (Geo-FuSE), Frequent Operator Combination Statistics (Geo-FuST), and Semantic Mapping (Geo-FuM). Techniques like Chain-of-Thought, TF-IDF, and the APRIORI algorithm are utilized to derive and align geospatial functions. An example knowledge base, Geo-FuB, built from 154,075 Google Earth Engine scripts, is available on GitHub. Evaluation metrics show a high accuracy, reaching 88.89% overall, with structural and semantic accuracies of 92.03% and 86.79% respectively. Geo-FuB's potential to optimize geospatial code generation through the RAG and fine-tuning paradigms is highlighted.
The widely adopted and powerful generative large language models (LLMs) have raised concerns about intellectual property rights violations and the spread of machine-generated misinformation. Watermarking serves as a promising approch to establish ownership, prevent unauthorized use, and trace the origins of LLM-generated content. This paper summarizes and shares the challenges and opportunities we found when watermarking LLMs. We begin by introducing techniques for watermarking LLMs themselves under different threat models and scenarios. Next, we investigate watermarking methods designed for the content generated by LLMs, assessing their effectiveness and resilience against various attacks. We also highlight the importance of watermarking domain-specific models and data, such as those used in code generation, chip design, and medical applications. Furthermore, we explore methods like hardware acceleration to improve the efficiency of the watermarking process. Finally, we discuss the limitations of current approaches and outline future research directions for the responsible use and protection of these generative AI tools.
With the rapid advancement of Large Language Models (LLMs), LLM-based approaches have demonstrated strong problem-solving capabilities across various domains. However, in automatic programming, a single LLM is typically limited to function-level code generation, while multi-agent systems composed of multiple LLMs often suffer from inefficient task planning. This lack of structured coordination can lead to cascading hallucinations, where accumulated errors across agents result in suboptimal workflows and excessive computational costs. To overcome these challenges, we introduce MaCTG (Multi-Agent Collaborative Thought Graph), a novel multi-agent framework that employs a dynamic graph structure to facilitate precise task allocation and controlled collaboration among LLM agents. MaCTG autonomously assigns agent roles based on programming requirements, dynamically refines task distribution through context-aware adjustments, and systematically verifies and integrates project-level code, effectively reducing hallucination errors and improving overall accuracy. MaCTG enhances cost-effectiveness by implementing a hybrid LLM deployment, where proprietary models handle complex reasoning, while open-source models are used for routine coding and validation tasks. To evaluate MaCTG's effectiveness, we applied it to traditional image processing auto-programming tasks, achieving a state-of-the-art accuracy of 83.33%. Additionally, by leveraging its hybrid LLM configuration, MaCTG significantly reduced operational costs by 89.09% compared to existing multi-agent frameworks, demonstrating its efficiency, scalability, and real-world applicability.
Large language models (LLMs) are being used in data science code generation tasks, but they often struggle with complex sequential tasks, leading to logical errors. Their application to geospatial data processing is particularly challenging due to difficulties in incorporating complex data structures and spatial constraints, effectively utilizing diverse function calls, and the tendency to hallucinate less-used geospatial libraries. To tackle these problems, we introduce GeoAgent, a new interactive framework designed to help LLMs handle geospatial data processing more effectively. GeoAgent pioneers the integration of a code interpreter, static analysis, and Retrieval-Augmented Generation (RAG) techniques within a Monte Carlo Tree Search (MCTS) algorithm, offering a novel approach to geospatial data processing. In addition, we contribute a new benchmark specifically designed to evaluate the LLM-based approach in geospatial tasks. This benchmark leverages a variety of Python libraries and includes both single-turn and multi-turn tasks such as data acquisition, data analysis, and visualization. By offering a comprehensive evaluation among diverse geospatial contexts, this benchmark sets a new standard for developing LLM-based approaches in geospatial data analysis tasks. Our findings suggest that relying solely on knowledge of LLM is insufficient for accurate geospatial task programming, which requires coherent multi-step processes and multiple function calls. Compared to the baseline LLMs, the proposed GeoAgent has demonstrated superior performance, yielding notable improvements in function calls and task completion. In addition, these results offer valuable insights for the future development of LLM agents in automatic geospatial data analysis task programming.
Large Language Models (LLMs) and Code-LLMs (CLLMs) have significantly improved code generation, but, they frequently face difficulties when dealing with challenging and complex problems. Retrieval-Augmented Generation (RAG) addresses this issue by retrieving and integrating external knowledge at the inference time. However, retrieval models often fail to find most relevant context, and generation models, with limited context capacity, can hallucinate when given irrelevant data. We present a novel framework that leverages a Programming Knowledge Graph (PKG) to semantically represent and retrieve code. This approach enables fine-grained code retrieval by focusing on the most relevant segments while reducing irrelevant context through a tree-pruning technique. PKG is coupled with a re-ranking mechanism to reduce even more hallucinations by selectively integrating non-RAG solutions. We propose two retrieval approaches-block-wise and function-wise-based on the PKG, optimizing context granularity. Evaluations on the HumanEval and MBPP benchmarks show our method improves pass@1 accuracy by up to 20%, and outperforms state-of-the-art models by up to 34% on MBPP. Our contributions include PKG-based retrieval, tree pruning to enhance retrieval precision, a re-ranking method for robust solution selection and a Fill-in-the-Middle (FIM) enhancer module for automatic code augmentation with relevant comments and docstrings.
Web development involves turning UI designs into functional webpages, which can be difficult for both beginners and experienced developers due to the complexity of HTML's hierarchical structures and styles. While Large Language Models (LLMs) have shown promise in generating source code, two major challenges persist in UI-to-HTML code generation: (1) effectively representing HTML's hierarchical structure for LLMs, and (2) bridging the gap between the visual nature of UI designs and the text-based format of HTML code. To tackle these challenges, we introduce Waffle, a new fine-tuning strategy that uses a structure-aware attention mechanism to improve LLMs' understanding of HTML's structure and a contrastive fine-tuning approach to align LLMs' understanding of UI images and HTML code. Models fine-tuned with Waffle show up to 9.00 pp (percentage point) higher HTML match, 0.0982 higher CW-SSIM, 32.99 higher CLIP, and 27.12 pp higher LLEM on our new benchmark WebSight-Test and an existing benchmark Design2Code, outperforming current fine-tuning methods.
Data selection is crucial for optimizing language model (LM) performance on specific tasks, yet most existing methods fail to effectively consider the target task distribution. Current approaches either ignore task-specific requirements entirely or rely on approximations that fail to capture the nuanced patterns needed for tasks like Autoformalization or code generation. Methods that do consider the target distribution often rely on simplistic, sometimes noisy, representations, like hashed n-gram features, which can lead to collisions and introduce noise. We introduce ZIP-FIT, a data selection framework that uses gzip compression to directly measure alignment between potential training data and the target task distribution. In extensive evaluations on Autoformalization and Python code generation, ZIP-FIT significantly outperforms leading baselines like DSIR and D4. Models trained on ZIP-FIT-selected data achieve their lowest cross-entropy loss up to 85.1\% faster than baselines, demonstrating that better task alignment leads to more efficient learning. In addition, ZIP-FIT performs selection up to 65.8\% faster than DSIR and two orders of magnitude faster than D4. Notably, ZIP-FIT shows that smaller, well-aligned datasets often outperform larger but less targeted ones, demonstrating that a small amount of higher quality data is superior to a large amount of lower quality data. Our results imply that task-aware data selection is crucial for efficient domain adaptation, and that compression offers a principled way to measure task alignment. By showing that targeted data selection can dramatically improve task-specific performance, our work provides new insights into the relationship between data quality, task alignment, and model learning efficiency.
Large Language Models have shown prominent capabilities in generating functional code from natural language descriptions. However, a standardized way to evaluate these capabilities in an objective and unbiased manner is still to be found. In this paper we review the current evaluation methods available to this end, and run a new evaluation of the performance of one state-of-the-art model (GPT4-o-mini) in solving curated coding challenges in 8 programming languages, obtained from Codewars, a software development community. Our analysis shows that the chance of success of the model has a positive correlation with the task difficulty, the popularity of the programming language being used and the time elapsed since the publication of the challenge. A further approximate explanatory analysis in terms of high-level features hints that while 46.6% of the model performance could be attributed to task difficulty, a 37.4% seems to be related to leakage of the challenge solutions into the model training set, while the remaining 16% depends on the programming language. These results suggest that current evaluation methodologies might be overestimating the actual skill of Large Language Models for generating functional code.
The recently introduced Mojo programming language (PL) by Modular, has received significant attention in the scientific community due to its claimed significant speed boost over Python. Despite advancements in code Large Language Models (LLMs) across various PLs, Mojo remains unexplored in this context. To address this gap, we introduce MojoBench, the first framework for Mojo code generation. MojoBench includes HumanEval-Mojo, a benchmark dataset designed for evaluating code LLMs on Mojo, and Mojo-Coder, the first LLM pretrained and finetuned for Mojo code generation, which supports instructions in 5 natural languages (NLs). Our results show that Mojo-Coder achieves a 30-35% performance improvement over leading models like GPT-4o and Claude-3.5-Sonnet. Furthermore, we provide insights into LLM behavior with underrepresented and unseen PLs, offering potential strategies for enhancing model adaptability. MojoBench contributes to our understanding of LLM capabilities and limitations in emerging programming paradigms fostering more robust code generation systems.
We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy. Motivated by recent work that predicts the probabilities of subsequent tokens using multiple heads, we connect this approach to rank-$1$ canonical tensor decomposition. By generalizing it to a rank-$r$ canonical probability decomposition, we develop an improved model that predicts multiple tokens simultaneously. This model can also be interpreted as a mixture of experts, allowing us to leverage successful techniques from that domain for efficient and robust training. Importantly, the overall overhead for training and sampling remains low. Our method demonstrates significant improvements in inference speed for both text and code generation tasks, proving particularly beneficial within the self-speculative decoding paradigm. It maintains its effectiveness across various model sizes and training epochs, highlighting its robustness and scalability.
Reinforcement Learning (RL) with unit test feedback has enhanced large language models (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental improvements. When generated code fails all unit tests, no learning signal is received, hindering progress on complex tasks. To address this, we propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement and providing immediate guidance. We explore various strategies for training PRMs and integrating them into the RL framework, finding that using PRMs both as dense rewards and for value function initialization significantly boosts performance. Our approach increases our in-house LLM's pass rate from 28.2% to 29.8% on LiveCodeBench and from 31.8% to 35.8% on our internal benchmark. Our experimental results highlight the effectiveness of PRMs in enhancing RL-driven code generation, especially for long-horizon scenarios.