Related papers: CAX-Agent: A Lightweight Agent Harness for Reliabl…

Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low…

AI agents, autonomous digital actors, need agent-native protocols; existing methods include GUI automation and MCP-based skills, with defects of high token consumption, fragmented interaction, inadequate security, due to lacking a unified…

Embodied robotic AI systems designed to manage complex daily tasks rely on a task planner to understand and decompose high-level tasks. While most research focuses on enhancing the task-understanding abilities of LLMs/VLMs through…

Large Language Models (LLMs) are increasingly used as autonomous agents in complex, long-horizon applications, where effective memory is critical for sustained performance. Yet existing memory benchmarks are largely dialogue-centric, while…

Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…

Software robots have long been used in Robotic Process Automation (RPA) to automate mundane and repetitive computer tasks. With the advent of Large Language Models (LLMs) and their advanced reasoning capabilities, these agents are now able…

Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer from (i) locally myopic generation, due to the absence of…

Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the network. Existing defenses face a fundamental dilemma: lightweight single-auditor methods are…

LLM agents have shown strong performance across a wide range of complex tasks, including interactive environments that require long-horizon decision making. But these agents cannot learn on the fly at test time. Self-evolving agents address…

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…

Agent-based AutoML systems rely on large language models to make complex, multi-stage decisions across data processing, model selection, and evaluation. However, existing evaluation practices remain outcome-centric, focusing primarily on…

Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its in-capability region. For tasks where the base policy…

Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents and disrupt the trajectory. In this paper, we present MASC,…

Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains…

The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses:…

Agent harnesses -- the stateful programs that wrap a language model and decide what it sees at each step -- are now known to change end-to-end performance on a fixed model by as much as six times. That raises a question asked less often…

Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for closed-set decision tasks such as routing, shortlisting, gating,…

LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…

Vulnerability detection tools are widely adopted in software projects, yet they often overwhelm maintainers with false positives and non-actionable reports. Automated exploitation systems can help validate these reports; however, existing…

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…