相关论文: Issue Localization via LLM-Driven Iterative Code G…

Providing timely and personalized guidance for students' programming assignments, offers significant practical value for helping students complete assignments and enhance their learning. In recent years, various automated Fault Localization…

Causal discovery is fundamental to scientific research, yet traditional statistical algorithms face significant challenges, including expensive data collection, redundant computation for known relations, and unrealistic assumptions. While…

Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that…

Large language models (LLMs) have demonstrated impressive reasoning abilities yet remain unreliable on knowledge-intensive, multi-hop questions -- they miss long-tail facts, hallucinate when uncertain, and their internal knowledge lags…

Human smuggling networks are complex and constantly evolving, making them difficult to analyze comprehensively. Legal case documents offer rich factual and procedural insights into these networks but are often long, unstructured, and filled…

Software crash bugs cause unexpected program behaviors or even abrupt termination, thus demanding immediate resolution. However, resolving crash bugs can be challenging due to their complex root causes, which can originate from issues in…

To perform effective causal inference in high-dimensional datasets, initiating the process with causal discovery is imperative, wherein a causal graph is generated based on observational data. However, obtaining a complete and accurate…

The rapid advancement of Large Language Models (LLMs) presents new opportunities for automated software vulnerability detection, a crucial task in securing modern codebases. This paper presents a comparative study on the effectiveness of…

We introduce GraphSL, a new library for studying the graph source localization problem. graph diffusion and graph source localization are inverse problems in nature: graph diffusion predicts information diffusions from information sources,…

Locating bugs is an important, but effort-intensive and time-consuming task, when dealing with large-scale systems. To address this, Information Retrieval (IR) techniques are increasingly being used to suggest potential buggy source code…

Automated fault localization requires connecting an observed test failure to the responsible method across thousands of candidates--a task that purely statistical approaches handle with limited precision and that LLMs cannot yet handle at…

We present CodeNav, an LLM agent that navigates and leverages previously unseen code repositories to solve user queries. In contrast to tool-use LLM agents that require ``registration'' of all relevant tools via manual descriptions within…

The impressive performance of Large Language Model (LLM) has prompted researchers to develop Multi-modal LLM (MLLM), which has shown great potential for various multi-modal tasks. However, current MLLM often struggles to effectively address…

Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.…

Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems. While automated reverse engineering tools can generate UML diagrams from code,…

Recent findings suggest that Information Retrieval (IR)-based bug localization techniques do not perform well if the bug report lacks rich structured information (eg relevant program entity names). Conversely, excessive structured…

Code quality evaluation involves scoring generated code quality based on a reference code for a specific problem statement. Currently, there are two main forms of evaluating code quality: match-based evaluation and execution-based…

The quality of output from large language models (LLMs), particularly in machine translation (MT), is closely tied to the quality of in-context examples (ICEs) provided along with the query, i.e., the text to translate. The effectiveness of…

Due to the impressive code comprehension ability of Large Language Models (LLMs), a few studies have proposed to leverage LLMs to locate bugs, i.e., LLM-based FL, and demonstrated promising performance. However, first, these methods are…

Recent research has shown that LLM performance on reasoning tasks can be enhanced by scaling test-time compute. One promising approach, particularly with decomposable problems, involves arranging intermediate solutions as a graph on which…