Related papers: SemanticALLI: Caching Reasoning, Not Just Response…
As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scientific workflows involving iterative data analysis and hypothesis refinement rapidly…
AI agent development relies heavily on natural language prompting to define agents' tasks, knowledge, and goals. These prompts are interpreted by Large Language Models (LLMs), which govern agent behavior. Consequently, agentic performance…
Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that…
In this study, a modular, data-free pipeline for multi-label intention recognition is proposed for agentic AI applications in transportation. Unlike traditional intent recognition systems that depend on large, annotated corpora and often…
Multimodal Artificial Intelligence (AI) systems, particularly Vision-Language Models (VLMs), have become integral to critical applications ranging from autonomous decision-making to automated document processing. As these systems scale,…
LLM-based agent applications have shown increasingly remarkable capabilities in complex workflows but incur substantial costs and latency due to extensive planning and reasoning requirements. Existing LLM caching techniques (like context…
Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under realistic conditions: binary-only feedback, no gradient…
As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…
Large foundation models enable powerful reasoning for autonomous systems, but mapping semantic intent to reliable real-time control remains challenging. Existing approaches either (i) let Large Language Models (LLMs) generate trajectories…
Cloud data pipelines increasingly operate under dynamic workloads, evolving schemas, cost constraints, and strict governance requirements. Despite advances in cloud-native orchestration frameworks, most production pipelines rely on static…
Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with external tools. This shift from static, single-turn inference to…
Recent advances in agentic frameworks have enabled AI agents to perform complex reasoning and decision-making. However, evidence comparing their reasoning performance, efficiency, and practical suitability remains limited. To address this…
Large language models can produce fluent judgments for clinical natural language inference, yet they frequently fail when the decision requires the correct inferential schema rather than surface matching. We introduce CARENLI, a…
Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice known as conceptual…
Clinical dialogue represents a complex duality requiring both the empathetic fluency of natural conversation and the rigorous precision of evidence-based medicine. While Large Language Models possess unprecedented linguistic capabilities,…
Visual reasoning -- the ability to interpret the visual world -- is crucial for embodied agents that operate within three-dimensional scenes. Progress in AI has led to vision and language models capable of answering questions from images.…
The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users.…
Agentic applications powered by Large Language Models exhibit non-deterministic behaviors that can form hidden execution cycles, silently consuming resources without triggering explicit errors. Traditional observability platforms fail to…
Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However,…
In high-stakes legal domains, retrieval must preserve not only semantic relevance, but also the hierarchy, temporality, and causal provenance of legal norms. Standard Retrieval-Augmented Generation (RAG), based mainly on semantic similarity…