Related papers: Plan with Code: Comparing approaches for robust NL…

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most…

Retrieval Augmented Generation (RAG) is a technique used to augment Large Language Models (LLMs) with contextually relevant, time-critical, or domain-specific information without altering the underlying model parameters. However,…

Optimizing software performance through automated code refinement offers a promising avenue for enhancing execution speed and efficiency. Despite recent advancements in LLMs, a significant gap remains in their ability to perform in-depth…

Software engineering activities such as package migration, fixing errors reports from static analysis or testing, and adding type annotations or other specifications to a codebase, involve pervasively editing the entire repository of code.…

Planning is a fundamental property of human intelligence. Reasoning about asynchronous plans is challenging since it requires sequential and parallel planning to optimize time costs. Can large language models (LLMs) succeed at this task?…

Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) for generating more factual, accurate, and up-to-date content. Existing methods either optimize prompts to guide LLMs in leveraging retrieved…

Recent availability of Large Language Models (LLMs) has led to the development of numerous LLM-based approaches aimed at providing natural language interfaces for various end-user tasks. These end-user tasks in turn can typically be…

Learned construction heuristics for scheduling problems have become increasingly competitive with established solvers and heuristics in recent years. In particular, significant improvements have been observed in solution approaches using…

Recent advances in code generation have illuminated the potential of employing large language models (LLMs) for general-purpose programming languages such as Python and C++, opening new opportunities for automating software development and…

Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly…

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, but these approaches…

Although Large Language Models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a…

The strong performance of large language models (LLMs) raises extensive discussion on their application to code generation. Recent research suggests continuous program refinements through visible tests to improve code generation accuracy in…

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Retrieval Augmented Generation (RAG) enables Large Language Models (LLMs) to generalize to new information by decoupling reasoning capabilities from static knowledge bases. Traditional RAG enhancements have explored vertical…

The advent of Large Language Models (LLMs) has significantly advanced the field of automated code generation. LLMs rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource…

There is a gap between our ability to reuse high-level concepts in software design and our ability to reuse the code implementing them. Language Oriented Programming (LOP) is a software development paradigm that aims to close this gap,…

Large Language Models (LLMs) are increasingly used in software development to generate functions, such as attack detectors, that implement security requirements. A key challenge is ensuring the LLMs have enough knowledge to address specific…

We proposed an end-to-end system design towards utilizing Retrieval Augmented Generation (RAG) to improve the factual accuracy of Large Language Models (LLMs) for domain-specific and time-sensitive queries related to private…

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…