Related papers: Multi-Agent Honeypot-Based Request-Response Contex…

Jailbreak attacks pose significant threats to large language models (LLMs), enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where…

Question-and-answer agents like ChatGPT offer a novel tool for use as a potential honeypot interface in cyber security. By imitating Linux, Mac, and Windows terminal commands and providing an interface for TeamViewer, nmap, and ping, it is…

Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens of thousands of tokens. This saturates context limits and increases computational cost…

Recognizing the promise of natural language interfaces to databases, prior studies have emphasized the development of text-to-SQL systems. While substantial progress has been made in this field, existing research has concentrated on…

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…

The deployment of Large Language Model (LLM)-generated SQL queries in Artificial Intelligence of Things (AIoT) systems introduces critical security risks, as prompt injection attacks can manipulate LLMs into producing unauthorized queries…

With the changing demographics of globalization, the emergence and prevalence of web application have acquired a central and pivotal role in the domains of technology and advancements. It thus becomes imperative to probe deeply into the…

DBMS bugs can cause serious consequences, posing severe security and privacy concerns. This paper works towards the detection of memory bugs and logic bugs in DBMSs, and aims to solve the two innate challenges, including how to generate…

The exponential growth of Internet traffic has made public servers increasingly vulnerable to unauthorized accesses and intrusions. In addition to maintaining low latency for the client, filtering unauthorized accesses has become one of the…

This paper proposes a query-level meta-agent named FlowReasoner to automate the design of query-level multi-agent systems, i.e., one system per user query. Our core idea is to incentivize a reasoning-based meta-agent via external execution…

This study introduces a new long-form database question answering dataset designed to evaluate how Large Language Models (LLMs) interact with a SQL interpreter. The task necessitates LLMs to strategically generate multiple SQL queries to…

Accurately retrieving relevant bid keywords for user queries is critical in Sponsored Search but remains challenging, particularly for short, ambiguous queries. Existing dense and generative retrieval models often fail to capture nuanced…

Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context…

We present a production-optimized multi-agent system designed to translate natural language queries into executable Python code for structured data analytics. Unlike systems that rely on expensive frontier models, our approach achieves high…

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…

The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…

In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate…

Mining software repositories often requires classifying artifacts like commits, reviews, code lines, or entire repositories into categories. Human labeling is expensive and error-prone; limited context frequently leads to misclassifications…

The application of language models to project-level vulnerability detection remains challenging, owing to the dual requirement of accurately localizing security-sensitive code and correctly correlating and reasoning over complex program…

Existing change detection methods often lack the versatility to handle diverse real-world queries and the intelligence for comprehensive analysis. This paper presents a general agent framework, integrating Large Language Models (LLM) with…