Related papers: Towards Optimal Agentic Architectures for Offensiv…

As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coordination framework…

Multi-agent systems (MAS) decompose complex tasks and delegate subtasks to different large language model (LLM) agents and tools. Prior studies have reported the superior accuracy performance of MAS across diverse domains, enabled by…

As the industry increasingly adopts agentic AI systems, understanding their unique vulnerabilities becomes critical. Prior research suggests that security flaws at the model level do not fully capture the risks present in agentic…

We present, to our knowledge, the most comprehensive cross-model evaluation of LLM agents on offensive cybersecurity tasks, benchmarking 10 frontier models from 7 providers on all 200 challenges of the NYU CTF Bench. Building on the…

Large language model(LLM)-driven multi-agent systems(MAS) coordinate specialized agents through predefined interaction topologies and have shown promise for complex tasks such as competition-level code generation. Recent studies demonstrate…

Agentic AI in software product development is increasingly adopted by organizations, yet the field lacks a consolidated synthesis of where adoption is mature, which architectural patterns dominate, and what limitations and coping mechanisms…

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

This paper presents a Unified Security Architecture that fortifies the Agentic Web through a Zero-Trust IAM framework. This architecture is built on a foundation of rich, verifiable agent identities using Decentralized Identifiers (DIDs)…

Cybersecurity is a relentless arms race, with AI driven offensive systems evolving faster than traditional defenses can adapt. Research and tooling remain fragmented across isolated defensive functions, creating blind spots that adversaries…

LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of…

Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete environment specifications, and brittle evaluation logic that human…

CTI-REALM (Cyber Threat Real World Evaluation and LLM Benchmarking) is a benchmark designed to evaluate AI agents' ability to interpret cyber threat intelligence (CTI) and develop detection rules. The benchmark provides a realistic…

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…

Large language models (LLMs) have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into patching systems. While prior work explores prompting strategies and individual agent designs,…

While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because real-world MAS are too complex to analyze entirely,…

With the rapid advancement of AI in code generation, cybersecurity detection engineering faces new opportunities to automate traditionally manual processes. Detection authoring - the practice of creating executable logic that identifies…

Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g.,…

Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on…