Related papers: Code-Optimise: Self-Generated Preference Data for …

Code-generating Large Language Models (LLMs) have become essential tools in modern software development, enhancing productivity and accelerating development. This paper aims to investigate the fine-tuning of code-generating LLMs using…

Scientific software is often driven by multiple parameters that affect both accuracy and performance. Since finding the optimal configuration of these parameters is a highly complex task, it extremely common that the software is used…

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Large language models (LLMs) have recently shown strong reasoning capabilities beyond traditional language tasks, motivating their use for numerical optimization. This paper presents LLMize, an open-source Python framework that enables…

Many systems require optimisation over multiple objectives, where objectives are characteristics of the system such as energy consumed or increase in time to perform the work. Optimisation is performed by selecting the `best' set of input…

Software model optimization is a process that automatically generates design alternatives aimed at improving quantifiable non-functional properties of software systems, such as performance and reliability. Multi-objective evolutionary…

To efficiently execute dynamically typed languages, many language implementations have adopted a two-tier architecture. The first tier aims for low-latency startup times and collects dynamic profiles, such as the dynamic types of variables.…

Predicting the runtime complexity of a programming code is an arduous task. In fact, even for humans, it requires a subtle analysis and comprehensive knowledge of algorithms to predict time complexity with high fidelity, given any code. As…

We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They…

Automatic code generation has gained significant momentum with the advent of Large Language Models (LLMs) such as GPT-4. Although many studies focus on improving the effectiveness of LLMs for code generation, very limited work tries to…

Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover solutions with superior complexity within limited budgets.…

Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision, which constrains scalability and hinders sustained self-improvement. Recent…

Despite the increase in popularity of language models for code generation, it is still unknown how training on bimodal coding forums affects a model's code generation performance and reliability. We, therefore, collect a dataset of over…

Code optimization is a challenging task requiring a substantial level of expertise from developers. Nonetheless, this level of human capacity is not sufficient considering the rapid evolution of new hardware architectures and software…

We approach the important challenge of code autocompletion as an open-domain task, in which a sequence-to-sequence code generator model is enhanced with the ability to attend to reference code snippets supplied by a semantic code search…

We formulate the loop-free, binary superoptimization task as a stochastic search problem. The competing constraints of transformation correctness and performance improvement are encoded as terms in a cost function, and a Markov Chain Monte…

Logical reasoning is a key task for artificial intelligence due to it's role in major downstream tasks such as Question Answering, Summarization. Recent methods in improving the reasoning ability of LLMs fall short in correctly converting a…

Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in…

This study explores a novel approach to enhance the performance of Large Language Models (LLMs) through the optimization of input data within prompts. While previous research has primarily focused on refining instruction components and…

Reimplementing solutions to previously solved software engineering problems is not only inefficient but also introduces inadequate and error-prone code. Many existing methods achieve impressive performance on this issue by using…