9 accepted papers
Current repository agents encounter a reasoning disconnect due to fragmented representations, as existing methods rely on isolated API documentation or dependency graphs that lack semantic depth. We consider repository comprehension and generation to be inverse processes within a unified cycle: gene…
Large language models excel at generating individual functions or single files of code, yet generating complete repositories from scratch remains a fundamental challenge. This capability is key to building coherent software systems from high-level specifications and realizing the full potential of a…
Given that Large Language Models (LLMs) are increasingly applied to automate software development, comprehensive software assurance spans three distinct goals: regression prevention, reactive reproduction, and proactive discovery. Current evaluations systematically overlook the third goal. Specifica…
Existing methods for code generation use code snippets as seed data, restricting the complexity and diversity of the synthesized data. In this paper, we introduce a novel feature tree-based synthesis framework, which revolves around hierarchical code features derived from high-level abstractions of…
Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for this capability. To fill this gap, we introduce FEA-Bench, a benchmark designed to assess the ability of large language mo…
Multiple-choice question (MCQ) datasets like Massive Multitask Language Understanding (MMLU) are widely used to evaluate the commonsense, understanding, and problem-solving abilities of large language models (LLMs). However, the open-source nature of these benchmarks and the broad sources of trainin…
Geologic map, as a fundamental diagram in geology science, provides critical insights into the structure and composition of Earth's subsurface and surface. These maps are indispensable in various fields, including disaster assessment, resource exploration, and civil engineering. Despite their signif…
Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success rates, with the candidate demonstrating a higher pass rate bei
Modern Automatic Speech Recognition (ASR) systems are evaluated with respect to Word Error Rate (WER). While WER is a useful metric for training and evaluation of speech models, it does not fully reflect the difference in semantics between predicted and ground truth transcriptions. In conversational…