Search: “agents”

arXiv:2505.10924v4 Announce Type: replace-cross Abstract: Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emul

arXiv:2604.26904v1 Announce Type: cross Abstract: Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around th

arXiv:2510.06002v3 Announce Type: replace Abstract: In high-stakes legal domains, retrieval must preserve not only semantic relevance, but also the hierarchy, temporality, and causal provenance of leg

arXiv:2604.21131v1 Announce Type: cross Abstract: AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips p

arXiv:2604.20911v1 Announce Type: cross Abstract: LLM agents deployed in production operate under operator-defined behavioral policies (system-prompt instructions such as prohibitions on credential di

arXiv:2604.20728v1 Announce Type: new Abstract: Autonomous systems that rely on learned perception can make unsafe decisions when sensor readings are misclassified. We study shielding for this setting

arXiv:2604.19064v1 Announce Type: new Abstract: In vision-and-language navigation (VLN), self-improvement from policy-induced experience, using only standard VLN action supervision, critically depends

arXiv:2604.16335v1 Announce Type: new Abstract: Despite recent progress in Large Language Model (LLM) Agents for Software Engineering (SWE) tasks, end-to-end fine-tuning typically relies on verifiable

arXiv:2511.12676v2 Announce Type: replace Abstract: Deploying embodied agents that can answer questions about their surroundings in realistic real-world settings remains difficult, partly due to the s

arXiv:2604.16706v1 Announce Type: cross Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated a

arXiv:2604.18349v1 Announce Type: new Abstract: Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions withou

arXiv:2603.20340v3 Announce Type: replace-cross Abstract: Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottlen

arXiv:2604.13097v1 Announce Type: cross Abstract: Embodied agents increasingly rely on modular capabilities that can be installed, upgraded, composed, and governed at runtime. Prior work has introduce

arXiv:2604.13888v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. How

arXiv:2604.13609v1 Announce Type: new Abstract: Reinforcement learners can attain high reward through novel unintended strategies. We study a Bayesian mitigation for general environments: we expand th

arXiv:2604.14004v1 Announce Type: cross Abstract: Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization

arXiv:2604.13579v1 Announce Type: new Abstract: Conventional Retrieval-Augmented Generation (RAG) systems often struggle with complex multi-hop queries over long documents due to their single-pass ret

arXiv:2604.11914v1 Announce Type: new Abstract: Self-monitoring capabilities -- metacognition, self-prediction, and subjective duration -- are often proposed as useful additions to reinforcement learn

arXiv:2601.07516v2 Announce Type: replace-cross Abstract: Vision-language models are increasingly employed as multimodal conversational agents (MCAs) for diverse conversational tasks. Recently, reinfo

arXiv:2604.09596v1 Announce Type: new Abstract: Dermatologic diseases impose a large and growing global burden, affecting billions and substantially reducing quality of life. While modern therapies ca

arXiv:2509.21982v2 Announce Type: replace Abstract: E-commerce risk management requires aggregating diverse, deeply embedded web data through multi-step, stateful interactions, which traditional scrap

arXiv:2604.11364v1 Announce Type: new Abstract: The two most influential cognitive architecture frameworks for AI agents, CoALA [21] and JEPA [12], both lack an explicit Knowledge layer with its own p

arXiv:2604.11557v1 Announce Type: new Abstract: Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However

arXiv:2508.04038v2 Announce Type: replace Abstract: Motion sensor time-series are central to Human Activity Recognition (HAR), yet conventional approaches are constrained to fixed activity sets and ty

arXiv:2604.08987v1 Announce Type: new Abstract: As Large Language Models (LLMs) advance toward embodied AI agents operating in physical environments, a fundamental question emerges: can models trained

arXiv:2604.09482v1 Announce Type: new Abstract: Reasoning in knowledge-intensive domains remains challenging as intermediate steps are often not locally verifiable: unlike math or code, evaluating ste

arXiv:2604.06562v1 Announce Type: new Abstract: Small language models (SLM) are increasingly used as interactive decision-making agents, yet most decision-oriented evaluations ignore emotion as a caus

arXiv:2610.18572v1 Announce Type: cross Abstract: Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically construct

arXiv:2610.06650v2 Announce Type: replace Abstract: Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right ent

arXiv:2609.36892v1 Announce Type: new Abstract: As the capabilities of large language models (LLMs) continue to advance, increasing attention is turning to how to translate their abilities into useful

arXiv:2609.37819v1 Announce Type: cross Abstract: Electronic invoices are replacing paper invoices worldwide, but today's centralized architectures leave three problems unsolved on the consumption sid

arXiv:2609.32569v1 Announce Type: new Abstract: Smart-home assistants are expected to handle diverse, realistic requests that arise in daily life. In such interactions, users often rely on the surroun

arXiv:2609.35432v1 Announce Type: new Abstract: Vision-language-action (VLA) and world-action (WAM) models map observations and instructions directly to robot actions. This directness ties a policy to

arXiv:2609.35576v1 Announce Type: cross Abstract: Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and

arXiv:2609.29389v1 Announce Type: new Abstract: Foundation vision-language models (VLMs) understand objects, instructions, and spatial relations, yet translating this capability into robotic manipulat

arXiv:2609.23407v1 Announce Type: cross Abstract: Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for emb

arXiv:2609.22090v1 Announce Type: new Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Psy

arXiv:2609.19138v1 Announce Type: cross Abstract: Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstration

arXiv:2609.10315v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code, where objective a

arXiv:2609.05036v1 Announce Type: new Abstract: AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value pluralism there is no correct target, but a shared prerequ

arXiv:2609.02760v1 Announce Type: new Abstract: On-premise assistants can give factory workers conversational access to machine documentation, but models capable of the task rarely fit shop-floor hard

arXiv:2609.02158v1 Announce Type: cross Abstract: Legal Judgment Prediction (LJP) models are typically trained on documents that describe facts from a prosecutorial perspective. Existing datasets furt

arXiv:2608.29481v1 Announce Type: new Abstract: Pediatric serious illness communication (SIC) is critically important, yet scalable communication training for clinicians remains limited. Compared with

arXiv:2608.27672v1 Announce Type: new Abstract: We present Qwen-GuidePlay-2B, a 2B-parameter language model for dialogue-game interaction. We fine-tune Qwen3.5-2B using three steps: a) SFT on only suc

arXiv:2510.12979v2 Announce Type: replace Abstract: Large language models (LLMs) augmented with multi-step reasoning and action generation abilities have shown promise in leveraging external tools to

arXiv:2603.01113v2 Announce Type: replace Abstract: Interactive task planning with large language models (LLMs) lets robots generate high-level action plans from natural language, but over long horizo