Related papers: RepoMirage: Probing Repository Context Reasoning i…
LLMs have demonstrated significant potential in code generation tasks, achieving promising results at the function or statement level across various benchmarks. However, the complexities associated with creating code artifacts like classes,…
Creating large-scale verifiable training datasets for issue-resolving tasks is a critical yet notoriously difficult challenge. Existing methods on automating the Gym environment setup process for real-world issues suffer from low success…
Code review generation can reduce developer effort by producing concise, reviewer-style feedback for a given code snippet or code change. However, generation-only models often produce generic or off-point reviews, while retrieval-only…
Recent advancements in large language models (LLMs) have demonstrated impressive capabilities in code translation, typically evaluated using benchmarks like CodeTransOcean and RepoTransBench. However, dependency-free benchmarks fail to…
Repository-aware code translation is critical for modernizing legacy systems, enhancing maintainability, and enabling interoperability across diverse programming languages. While recent advances in large language models (LLMs) have improved…
Repository summarization is a crucial research question in development and maintenance for software engineering. Existing repository summarization techniques primarily focus on summarizing code according to the directory tree, which is…
Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite…
Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior…
Code Agent development is an extremely active research area, where a reliable performance metric is critical for tracking progress and guiding new developments. This demand is underscored by the meteoric rise in popularity of SWE-Bench.…
Code search has usually been evaluated as first-stage retrieval, even though production systems rely on broader pipelines with reranking and developer-style queries. Existing benchmarks also suffer from data contamination, label noise, and…
Retrieval-augmented generation (RAG) systems trained using reinforcement learning (RL) with reasoning are hampered by inefficient context management, where long, noisy retrieved documents increase costs and degrade performance. We introduce…
Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily constrain an agent's design decision space, making it…
This paper presents a multi-stage reranking system for repository-level code search, which leverages the vastly available commit histories of large open-source repositories to aid in bug fixing. We define the task of repository-level code…
Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retrieval-augmented generation (RAG) frameworks are widely adopted,…
Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often overlook the long tail topics and rely on popular repositories…
Agentic systems have been widely studied to automate software engineering jobs such as bug fixing. As these systems increasingly tackle complex tasks, understanding where and why they fail becomes essential for iterative refinement and…
Recent Large Language Models (LLMs) have reported high accuracy on reasoning benchmarks. However, it is still unclear whether the observed results arise from true reasoning or from statistical recall of the training set. Inspired by the…
Generative models have demonstrated considerable potential in software engineering, particularly in tasks such as code generation and debugging. However, their utilization in the domain of code documentation generation remains…