Related papers: AgentModernize: Preserving Business Logic in Legac…

AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no unified benchmark enables fair comparison across these approaches. We present Agentick, a…

Bug localization remains a critical yet time-consuming challenge in large-scale software repositories. Traditional information retrieval-based bug localization (IRBL) methods rely on unchanged bug descriptions, which often contain noisy…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Modern work relies on an assortment of digital collaboration tools, yet routine processes continue to suffer from human error and delay. To address this gap, this dissertation extends TheAgentCompany with a finance-focused environment and…

Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent research has increasingly concentrated on Retrieval-Augmented…

Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce…

Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…

Software development agents powered by large language models (LLMs) have shown great promise in automating tasks like environment setup, issue solving, and program repair. Unfortunately, understanding and debugging such agents remain…

Identifying Bug-Inducing Commits (BICs) is fundamental for understanding software defects and enabling downstream tasks such as defect prediction and automated program repair. Yet existing SZZ-based approaches rely on git blame, restricting…

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Large Language Models (LLMs) are increasingly deployed within agentic systems - collections of interacting, LLM-powered agents that execute complex, adaptive workflows using memory, tools, and dynamic planning. While enabling powerful new…

Numerous methods have been proposed to measure LLM misgendering, including probability-based evaluations (e.g., automatically with templatic sentences) and generation-based evaluations (e.g., with automatic heuristics or human validation).…

Large language model (LLM) based agents are increasingly used to tackle software engineering tasks that require multi-step reasoning and code modification, demonstrating promising yet limited performance. However, most existing LLM agents…

Static analyzers play a critical role in identifying bugs early in the software development lifecycle, but their rule implementations are often under-tested and prone to inconsistencies. To address this, we propose StaAgent, an agentic…

Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strategy, feature engineering, and hyperparameters. Traditional approaches treat these dimensions…

In this paper, we aim to improve the reasoning ability of large language models (LLMs) over knowledge graphs (KGs) to answer complex questions. Inspired by existing methods that design the interaction strategy between LLMs and KG, we…

Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic,…

Modern agentic frameworks (e.g., CrewAI and AutoGen) have evolved into complex, autonomous multi-agent systems, introducing unique reliability challenges beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus…

Automatically extracting workflows as procedural graphs from natural language is promising yet underexplored, demanding both structural validity and logical alignment. While recent large language models (LLMs) show potential for procedural…