Related papers: S-Bus: Automatic Read-Set Reconstruction for Multi…

Existing benchmarks for Large Language Model (LLM) agents focus on task completion under idealistic settings but overlook reliability in real-world, user-facing applications. In domains, such as in-car voice assistants, users often issue…

AI-powered edge computing security is moving Intelligent Transportation Systems (ITS) from passive, rule-based protections to proactive, smart, zero-touch, self-sufficient safeguards that neutralize threats in milliseconds. As…

While virtualization and resource pooling empower cloud networks with structural flexibility and elastic scalability, they inevitably expand the attack surface and challenge cyber resilience. Reinforcement Learning (RL)-based defense…

This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP. We find that the distribution shift settings in previous studies commonly lack adequate challenges, hindering the accurate evaluation of OOD…

We present L-MARS (Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search), a multi-agent retrieval framework for grounded legal question answering that decomposes queries into structured sub-problems, retrieves evidence…

Multi-agent systems (MAS) based on Large Language Models (LLMs) have the potential to solve tasks that are beyond the reach of any single LLM. However, this potential can only be realized when the collaboration mechanism between agents is…

Large language models (LLMs) are increasingly integrated into autonomous systems, giving rise to a new class of software known as Agentware, where LLM-powered agents perform complex, open-ended tasks in domains such as software engineering,…

Semi-supervised learning (SSL) enables prediction with limited labels, but high-stakes tabular applications (medical, credit, recidivism) require statistical fairness guarantees. We identify a structural conflict in tabular fair SSL through…

LLM agents are increasingly deployed to plan, retrieve, and write with tools, yet evaluation still leans on static benchmarks and small human studies. We present the Agent-Testing Agent (ATA), a meta-agent that combines static code…

LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…

Multi-agent LLM orchestration incurs synchronization costs scaling as O(n x S x |D|) in agents, steps, and artifact size under naive broadcast -- a regime I term broadcast-induced triply-multiplicative overhead. I argue this pathology is a…

Generative recommendation models sequence generation to produce items end-to-end, but training from behavioral logs often provides weak supervision on underlying user intent. Although Large Language Models (LLMs) offer rich semantic priors…

Ride-hailing platforms face significant challenges in optimizing order dispatching and driver repositioning operations in dynamic urban environments. Traditional approaches based on combinatorial optimization, rule-based heuristics, and…

Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…

Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with distributed information, rather than merely…

Cloud environments face frequent DDoS threats due to centralized resources and broad attack surfaces. Modern cloud-native DDoS attacks further evolve rapidly and often blend multi-vector strategies, creating an operational dilemma:…

Single large language models (LLMs) often fall short when faced with the ever-growing range of tasks, making a single-model approach insufficient. We address this challenge by proposing ORI (O Routing Intelligence), a dynamic framework that…

Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools,…

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to…

Autonomous indoor mobile robots can navigate reliably to metric coordinates using established frameworks such as ROS 2 Navigation 2, yet they lack the ability to interpret natural language instructions that express intent rather than…