Search: “agents”

arXiv:2606.05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow

arXiv:2606.05342v1 Announce Type: new Abstract: AI agents are increasingly asked to carry out work that spans minutes, hours, or longer. Yet the default model of agent behavior is continuous action: i

arXiv:2606.03374v1 Announce Type: new Abstract: We present eMEM (Embodied Memory), a hybrid graph-based memory system for embodied agents operating in physical environments. Current agent memory archi

arXiv:2606.00756v1 Announce Type: new Abstract: Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-const

arXiv:2606.00408v1 Announce Type: cross Abstract: Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly importa

arXiv:2606.02031v1 Announce Type: cross Abstract: Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despit

arXiv:2509.22504v3 Announce Type: replace Abstract: As language model (LM) agents become increasingly capable and adopted in real-world applications, there is a growing need for scalable evaluation fr

arXiv:2605.28840v1 Announce Type: cross Abstract: Large language model (LLM) agents with tool-calling capabilities are increasingly deployed in production systems, yet a fundamental reliability questi

arXiv:2605.28607v1 Announce Type: new Abstract: Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transiti

arXiv:2605.27905v1 Announce Type: new Abstract: AI research agents can now generate research ideas, design experiments, run code, and draft papers, raising the possibility of large-scale AI-assisted s

arXiv:2605.28359v1 Announce Type: new Abstract: Evaluating whether large language model (LLM) agents can profit in capital markets is increasingly framed as end-to-end trading: place an agent in a his

arXiv:2605.27999v1 Announce Type: cross Abstract: We address the problem of learning to assign prediction tasks to one agent from a set of available human or AI agents. In particular, we focus on the

arXiv:2605.27825v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure p

arXiv:2605.26154v1 Announce Type: cross Abstract: LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents

arXiv:2605.26256v1 Announce Type: new Abstract: Multimodal large language model (MLLM)-based embodied agents have shown strong potential for solving complex tasks in physical environments. However, pe

arXiv:2605.24110v1 Announce Type: new Abstract: Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assess

arXiv:2605.20173v1 Announce Type: new Abstract: Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a firs

arXiv:2605.20049v1 Announce Type: cross Abstract: As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. Thi

arXiv:2603.03140v3 Announce Type: replace-cross Abstract: AI agents are increasingly active on social media platforms, generating content and interacting with one another at scale. Yet the behavioral

arXiv:2605.16819v1 Announce Type: cross Abstract: GPU kernel optimization is increasingly critical for efficient deep learning systems, but writing high-performance kernels still requires substantial

arXiv:2605.18535v1 Announce Type: new Abstract: The bottleneck of useful agentic intelligence has shifted from compressing world knowledge into a single model to executing a coordinated system. This p

arXiv:2605.18703v1 Announce Type: new Abstract: Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robus

arXiv:2605.17734v1 Announce Type: new Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizo

arXiv:2602.02262v3 Announce Type: replace-cross Abstract: LLM-powered coding agents are redefining how real-world software is developed. To drive the research towards better coding agents, we require

arXiv:2605.17830v1 Announce Type: new Abstract: Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under

arXiv:2605.18332v1 Announce Type: cross Abstract: Behavioral studies of LLM-based software engineering agents extract operational rules about which trajectory shapes correlate with higher resolution r

arXiv:2605.15812v1 Announce Type: cross Abstract: Recent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet mos

arXiv:2605.14556v1 Announce Type: new Abstract: Symmetrical Reality (SR) is emerging as a future trend for human-agent coexistence, placing higher demands on agents to acquire human-like intelligence.

arXiv:2605.15030v1 Announce Type: cross Abstract: Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to p

arXiv:2605.13357v1 Announce Type: cross Abstract: Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development se

arXiv:2512.12634v3 Announce Type: replace Abstract: Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer inte

arXiv:2605.12411v1 Announce Type: cross Abstract: AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant ne

arXiv:2605.08813v1 Announce Type: new Abstract: Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal com

arXiv:2605.09698v1 Announce Type: new Abstract: As data-science agents shift from co-pilots to auto-pilots, silent misframing becomes a critical failure mode. Agents quietly commit to plausible but un

arXiv:2602.10356v2 Announce Type: replace Abstract: Real-world digital environments are highly diverse and dynamic. These characteristics cause agents to frequently encounter unseen environments and d

arXiv:2605.10779v1 Announce Type: cross Abstract: The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content s

arXiv:2605.08257v1 Announce Type: cross Abstract: Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develo

arXiv:2605.06737v1 Announce Type: cross Abstract: Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a si

arXiv:2512.10371v2 Announce Type: replace Abstract: The rapid development of mobile GUI agents has stimulated growing research interest in long-horizon task automation. However, building agents for th

arXiv:2603.06859v2 Announce Type: replace-cross Abstract: Removing an agent from a cooperative team to measure its contribution seems natural, yet in multi-agent LLM systems this evaluation distorts t

arXiv:2603.24755v2 Announce Type: replace-cross Abstract: Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmar

arXiv:2605.04036v1 Announce Type: cross Abstract: Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominat

arXiv:2605.01489v1 Announce Type: cross Abstract: Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents

arXiv:2604.27996v1 Announce Type: new Abstract: This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate vi

arXiv:2604.27872v1 Announce Type: new Abstract: Large language model (LLM) agents deployed in clinical settings often exhibit abrupt, threshold-driven behavior, offering little visibility into accumul

arXiv:2604.27264v1 Announce Type: cross Abstract: Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time,