Search: “agents”

arXiv:2605.08580v1 Announce Type: cross Abstract: To cope with the large contexts that long-horizon LLM agents produce, modern frameworks increasingly rely on compaction -- invoking an LLM to rewrite

arXiv:2605.09104v1 Announce Type: new Abstract: As LLM agents evolve, tokens have emerged as the core economic primitives of Agentic AI. However, their exponential consumption introduces severe comput

arXiv:2605.06869v1 Announce Type: new Abstract: AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no u

arXiv:2510.25224v3 Announce Type: replace Abstract: While Large Language Models (LLMs) are increasingly used in agentic frameworks to assist individual users, there is a growing need for agents that c

arXiv:2605.01986v1 Announce Type: new Abstract: What if the twelve jurors of Sidney Lumet's 12 Angry Men (1957) were not men, but large language models? Would the one juror who disagrees still be able

arXiv:2604.25847v1 Announce Type: cross Abstract: Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problem

arXiv:2604.19775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments.

arXiv:2511.11793v3 Announce Type: replace Abstract: We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike

arXiv:2604.18860v1 Announce Type: cross Abstract: GUI agents that control desktop computers via screenshot-and-click loops introduce a new class of vulnerability: the observation-to-action gap (mean 6

arXiv:2604.18271v1 Announce Type: new Abstract: As the world of agentic artificial intelligence applied to robotics evolves, the need for agents capable of building and retrieving memories and observa

arXiv:2511.09149v4 Announce Type: replace Abstract: While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint. The process of downsampling

arXiv:2603.01692v3 Announce Type: replace-cross Abstract: LLM-based agents for machine learning engineering (MLE) predominantly rely on tree search, a form of gradient-free optimization that uses scal

arXiv:2604.07927v2 Announce Type: replace Abstract: Deep research requires reasoning over web evidence to answer open-ended questions, and it is a core capability for AI agents. Yet many deep research

arXiv:2604.06240v1 Announce Type: cross Abstract: Verifying the success of computer use agent (CUA) trajectories is a critical challenge: without reliable verification, neither evaluation nor training

arXiv:2604.06367v1 Announce Type: cross Abstract: Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate

arXiv:2610.15390v1 Announce Type: cross Abstract: Audio Large Language Models (Audio LLMs) are embedded in agents for smart homes, vehicles, wearables, and embodied systems, where acoustic inputs can

arXiv:2610.14350v1 Announce Type: cross Abstract: Having demonstrated a strong potential for automating vulnerability discovery, AI agents can also be used to attack software systems at scale. Today's

arXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing

arXiv:2610.13064v1 Announce Type: new Abstract: Large Language Model (LLM) agents have demonstrated remarkable capabilities in tackling complex tasks through agentic workflows. However, manually desig

arXiv:2606.16215v2 Announce Type: replace-cross Abstract: Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns. Post-training such agents is c

arXiv:2610.12651v1 Announce Type: new Abstract: LLM agents executing multi-step workflows fail in two fundamentally different ways: recoverable slips, which further attempts can repair, and knowledge

arXiv:2512.11147v2 Announce Type: replace-cross Abstract: AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a

arXiv:2610.08082v1 Announce Type: new Abstract: LLM tool-use agents operate in dynamic environments where many actions carry operational risk. However, most safety mechanisms react only after errors m

arXiv:2610.06514v1 Announce Type: cross Abstract: The growing adoption of large language model (LLM) agents creates a need for network administrators and security teams to audit agent behavior within

arXiv:2610.04800v1 Announce Type: cross Abstract: Graphical consoles offer a practical interface for medical acquisition assistance, allowing agents to work through the controls and visual feedback us

arXiv:2610.02654v1 Announce Type: new Abstract: Models of social contagion usually assume how individuals adopt beliefs and derive population behavior from it. We instead empirically measure belief ad

arXiv:2610.03020v1 Announce Type: new Abstract: Long-term agents must remember not only what is true about a user, but also how a particular agent should work with that user as their shared history ev

arXiv:2610.02459v1 Announce Type: new Abstract: Coding agents are extending their reach into the physical world by writing and executing robot control programs. One might expect the agents to use the

arXiv:2610.02569v1 Announce Type: cross Abstract: Coding agents have become increasingly long-horizon, autonomous, reliant on general-purpose shell and maintain their own persistent memory for self-im

arXiv:2610.03356v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly deployed in high-stakes settings such as industrial maintenance and equipment fault troubleshooting,

arXiv:2610.03089v1 Announce Type: cross Abstract: Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt

arXiv:2610.03195v1 Announce Type: new Abstract: As LLM agents decide on users' behalf which product to buy, which hotel to book, or which paper to cite, a preference for items from certain sources (th

arXiv:2610.01564v1 Announce Type: cross Abstract: LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowin

arXiv:2610.00435v1 Announce Type: cross Abstract: We study how AI agents discover and validate scientific formulas using a controlled case study of the hydrotope, a recently discovered geometric formu

arXiv:2610.01787v1 Announce Type: new Abstract: Self-improving GUI agents keep the trajectories they produce and return them to the agent, by fine-tuning or by retrieval into the prompt, and studies t

arXiv:2610.00650v1 Announce Type: cross Abstract: The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted an

arXiv:2609.39564v1 Announce Type: new Abstract: Delegating complete application development to coding agents requires preserving the intended design rather than simply producing plausible outputs thro

arXiv:2609.38296v1 Announce Type: new Abstract: Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other. To investigate th

arXiv:2609.38536v1 Announce Type: cross Abstract: Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, b

arXiv:2609.38782v1 Announce Type: new Abstract: Conversational agents increasingly interact with children, yet evidence on how their design shapes children's susceptibility to persuasion comes almost

arXiv:2609.33812v1 Announce Type: cross Abstract: Repeated runs of the same coding agent are known to give different benchmark scores. We ask what that variation means for a team running an agent on i

arXiv:2609.34321v1 Announce Type: new Abstract: GUI agents are deployed with frozen weights and discard everything they experience on the job. Existing ways to update an agent's weights assume somethi

arXiv:2609.33378v1 Announce Type: cross Abstract: A central goal in robotics is to enable manipulation across changing tasks and environments. Vision-language-action (VLA) models provide broad manipul

arXiv:2609.30725v1 Announce Type: new Abstract: Although effective, coding agents often incur substantial monetary costs. Their recurring cost-inefficient behaviors remain underexplored. We conduct th

arXiv:2609.31076v1 Announce Type: new Abstract: Language agents struggle to act and learn in environments that require long sequences of low-level actions. Code-based abstractions can make these agent

arXiv:2609.29547v1 Announce Type: cross Abstract: Agentic AI is sold on a simple promise: the system keeps acting when the user stops watching. That promise creates an accountability inversion. As ste