Search: “agents”

arXiv:2605.17453v1 Announce Type: cross Abstract: Tool-using LLM agents increasingly rely on external tools to make consequential decisions, yet most existing agent-security benchmarks and defenses im

arXiv:2605.15768v1 Announce Type: new Abstract: Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving cont

arXiv:2512.01089v2 Announce Type: replace Abstract: Automated Scientific Discovery (ASD) systems can help automatically generate and run code-based experiments, but their capabilities are limited by t

arXiv:2605.16116v1 Announce Type: new Abstract: Developing and evaluating e-commerce web agents requires environments that preserve meaningful task structure while enabling controllable, reproducible,

arXiv:2605.15581v1 Announce Type: new Abstract: LLM-based root cause analysis (RCA) agents have recently emerged as a promising paradigm for incident diagnosis in microservice AIOps. However, their re

arXiv:2605.14322v1 Announce Type: new Abstract: Language agents are increasingly deployed in complex professional workflows, with tutoring emerging as a particularly high-stakes capability that remain

arXiv:2510.02837v2 Announce Type: replace Abstract: Although recent tool-augmented benchmarks involve complex requests, evaluation remains limited to answer matching, neglecting critical trajectory as

arXiv:2605.14033v1 Announce Type: new Abstract: Scientific theory shift in AI agents requires more than fitting equations to data. An artificial scientific agent must detect whether an existing repres

arXiv:2605.11388v1 Announce Type: new Abstract: Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity t

arXiv:2605.11086v1 Announce Type: cross Abstract: AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is

arXiv:2605.12233v1 Announce Type: new Abstract: Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret

arXiv:2410.13181v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) have been remarkable. Users face a choice between using cloud-based LLMs for generation quality

arXiv:2605.09826v1 Announce Type: new Abstract: Theory of Mind (ToM), the ability to track others epistemic state, makes humans efficient collaborators. AI agents need the same capacity in multi agent

arXiv:2605.09317v1 Announce Type: new Abstract: GUI agents are beginning to operate the web, mobile, and desktop as interactive worlds, where successful control depends on carrying forward visual, pro

arXiv:2508.15294v4 Announce Type: replace Abstract: In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on ex

arXiv:2605.07505v1 Announce Type: new Abstract: Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device

arXiv:2508.16571v4 Announce Type: replace Abstract: In this paper, we describe and benchmark a competitor-discovery component used within an agentic AI system for fast drug asset due diligence. A comp

arXiv:2605.07134v1 Announce Type: cross Abstract: Web agents perceive web pages through an observation space, yet its granularity has remained an underexamined design choice. Existing work treats obse

arXiv:2605.07164v1 Announce Type: new Abstract: Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is const

arXiv:2605.06898v1 Announce Type: new Abstract: At the heart of existing language model agents is a fixed orchestrator program responsible for the state transition between consecutive turns. This pape

arXiv:2605.04449v1 Announce Type: new Abstract: Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models

arXiv:2605.03159v1 Announce Type: new Abstract: As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing appro

arXiv:2605.03353v1 Announce Type: cross Abstract: LLM-Agents have evolved into autonomous systems for complex task execution, with the SKILL.md specification emerging as a de facto standard for encaps

arXiv:2605.02240v1 Announce Type: new Abstract: We introduce PhysicianBench, a benchmark for evaluating LLM agents on physician tasks grounded in real clinical setting within electronic health record

arXiv:2510.08952v4 Announce Type: replace Abstract: Text-attributed graphs (TAGs) have become a key form of graph-structured data in modern data management and analytics, combining structural relation

arXiv:2605.00136v1 Announce Type: new Abstract: Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we

arXiv:2604.27776v1 Announce Type: new Abstract: While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single

arXiv:2604.25380v1 Announce Type: new Abstract: Recent advancements in Graphical User Interface (GUI) agents have predominantly focused on training paradigms like supervised fine-tuning (SFT) and rein

arXiv:2604.24964v1 Announce Type: cross Abstract: Existing web agent benchmarks have largely converged on short, single-site tasks that frontier models are approaching saturation on. However, real wor

arXiv:2603.14248v2 Announce Type: replace-cross Abstract: Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizo

arXiv:2604.24038v1 Announce Type: new Abstract: Static benchmarks measure what AI agents can do at a fixed point in time but not how they are adopted, maintained, or experienced in deployment. We intr

arXiv:2604.23781v1 Announce Type: new Abstract: Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surroundi

arXiv:2604.05013v2 Announce Type: replace-cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting

arXiv:2604.20006v1 Announce Type: new Abstract: Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. Ho

arXiv:2512.09756v2 Announce Type: replace Abstract: Role-playing agents (RPAs) require balancing multiple objectives, such as instruction following, persona consistency, and stylistic fidelity, which

arXiv:2604.18375v1 Announce Type: new Abstract: Conversational agents, such as ChatGPT and Doubao, have become essential daily assistants for billions of users. To further enhance engagement, these sy

arXiv:2604.16813v1 Announce Type: cross Abstract: Agentic AI systems are rapidly advancing toward real-world applications, yet their readiness in complex and personalized environments remains insuffic

arXiv:2505.19897v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have extended their impact beyond Natural Language Processing, substantially fostering the development of interdi

arXiv:2604.13108v1 Announce Type: cross Abstract: AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with for

arXiv:2604.15037v1 Announce Type: cross Abstract: Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existi

arXiv:2604.15093v1 Announce Type: cross Abstract: Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achie

arXiv:2604.12116v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents capable of executing system-level operations. While existing benchmarks

arXiv:2510.05188v2 Announce Type: replace Abstract: Although LLMs have been widely adopted for creative content generation, a single-pass process often struggles to produce high-quality long narrative

arXiv:2604.07791v2 Announce Type: replace Abstract: Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. Wit

arXiv:2509.22097v3 Announce Type: replace-cross Abstract: Large language model-powered code agents are rapidly transforming software engineering, yet the security risks of their generated code have be

arXiv:2602.07142v2 Announce Type: replace-cross Abstract: Collaboration is a cornerstone of 21st-century learning, yet teachers continue to face challenges in supporting productive peer interaction. E