Search: “agents”

arXiv:2607.07946v1 Announce Type: cross Abstract: DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents. Most public agentic coding benchmarks fo

arXiv:2607.08395v1 Announce Type: cross Abstract: Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-lived software systems. Unlike traditional chat assi

arXiv:2607.07474v1 Announce Type: cross Abstract: Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not. We argue that th

arXiv:2607.05518v1 Announce Type: cross Abstract: AI agents issue tool calls on the basis of text they cannot verify, so any party who controls part of the context can forge the appearance of authorit

arXiv:2607.06223v1 Announce Type: new Abstract: Reinforcement learning has become a promising paradigm for improving large language model (LLM) agents on long-horizon search tasks, where the agent mus

arXiv:2507.22758v2 Announce Type: replace Abstract: Recent advancements in financial problem-solving have leveraged LLMs and agent-based systems, with a primary focus on trading and financial modeling

arXiv:2607.05743v1 Announce Type: cross Abstract: AI coding agents now read repositories, call tools, and execute shell commands with limited human oversight, and a fast-growing body of work studies w

arXiv:2606.20023v2 Announce Type: replace-cross Abstract: As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, pri

arXiv:2508.07033v2 Announce Type: replace Abstract: Embodied agents have shown promising generalization capabilities across diverse physical environments, making them essential for a wide range of rea

arXiv:2607.05363v1 Announce Type: new Abstract: Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-mediated information, use tools, and negot

arXiv:2510.06288v4 Announce Type: replace Abstract: Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set b

arXiv:2607.02496v1 Announce Type: cross Abstract: Realistic traffic simulation requires agents that imitate logged behavior and can also be steered along interpretable axes. Such controllability enabl

arXiv:2511.10687v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled w

arXiv:2607.00436v1 Announce Type: new Abstract: Large language model agents are increasingly connected to scientific software, yet it remains unclear when tool access makes scientific computation more

arXiv:2606.31522v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized with explicit behavioral mandates such as 'preserve

arXiv:2606.30697v1 Announce Type: cross Abstract: Current operating systems expose interfaces optimized for human users but not for AI agents. Humans benefit from pixels, icons, windows, visual groupi

arXiv:2606.31612v1 Announce Type: new Abstract: Mobile GUI agents increasingly face long-horizon tasks that require reading, updating, and reusing task-relevant data across pages and applications. Exi

arXiv:2606.30454v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as agents in simulations of social systems, yet it remains unclear when their behavior can be inter

arXiv:2510.14207v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jail

arXiv:2606.22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget. We show t

arXiv:2606.28514v1 Announce Type: new Abstract: Multimodal models are increasingly deployed to solve tasks collaboratively with humans or other artificial agents. Existing benchmarks show that these m

arXiv:2606.29459v1 Announce Type: cross Abstract: Inverse design of metal-organic frameworks (MOFs) requires searching a combinatorially vast space where property labels are expensive and most machine

arXiv:2606.28356v1 Announce Type: cross Abstract: Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems. In recommendation age

arXiv:2606.28480v1 Announce Type: cross Abstract: As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader ra

arXiv:2606.27499v1 Announce Type: cross Abstract: Research on agent memory has matured rapidly, but almost entirely on the text side: few existing benchmarks ask, in an interactive environment, when a

arXiv:2606.27397v1 Announce Type: cross Abstract: Evaluating LLM agents requires dynamic environments that go beyond static reasoning and zero-sum games. Real-world economic interaction is often open-

arXiv:2606.28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments

arXiv:2606.27330v1 Announce Type: cross Abstract: Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks in

arXiv:2606.26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places co

arXiv:2606.25760v1 Announce Type: cross Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejec

arXiv:2606.24392v1 Announce Type: new Abstract: Existing ECG report generation is tightly coupled -- interpretation and reporting fused end-to-end, so errors propagate without stage-level recourse --

arXiv:2606.24453v1 Announce Type: new Abstract: Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive verifiers. The tool-use decisions are typically g

arXiv:2605.06177v2 Announce Type: replace Abstract: Reproducing and comparing deep research agents today is hard: the same backbone evaluated on the same benchmark can report different accuracies acro

arXiv:2606.24151v1 Announce Type: cross Abstract: Self-evolving agents improve over time by distilling experience from past executions and reusing it in future tasks. Existing systems represent such e

arXiv:2606.24597v1 Announce Type: new Abstract: A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning.

arXiv:2606.24820v1 Announce Type: new Abstract: LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated l

arXiv:2606.24470v1 Announce Type: new Abstract: A real-time agent for general computer use - with games as the most demanding case - must act within tens of milliseconds while still planning over seco

arXiv:2606.24842v1 Announce Type: new Abstract: In the big-world regime, agents cannot be universally capable and their ability is inevitably specialized across a world model in pieces. Consequently,

arXiv:2603.20179v3 Announce Type: replace-cross Abstract: Large language model-based AI agents are now able to autonomously execute substantial portions of a high energy physics (HEP) analysis pipelin

arXiv:2606.11213v1 Announce Type: new Abstract: We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a

arXiv:2606.11998v1 Announce Type: new Abstract: Trusted monitoring is a cornerstone of AI control. However, as frontier models grow more capable, the increasing capabilities gap between trusted and un

arXiv:2606.10742v1 Announce Type: cross Abstract: External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences. However,

arXiv:2606.11070v1 Announce Type: cross Abstract: Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems. However,

arXiv:2606.09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.g., workspace files or logs). Consequently, jailbreak

arXiv:2605.22664v2 Announce Type: replace Abstract: LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions. To meet ente

arXiv:2606.07943v1 Announce Type: cross Abstract: Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A pr