Related papers: Explainable Model Routing for Agentic Workflows
Large language models (LLMs) are increasingly integrated into autonomous systems, giving rise to a new class of software known as Agentware, where LLM-powered agents perform complex, open-ended tasks in domains such as software engineering,…
Agents are a special kind of AI-based software in that they interact in complex environments and have increased potential for emergent behaviour. Explaining such emergent behaviour is key to deploying trustworthy AI, but the increasing…
Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle on complex tasks. Static escalation rules and keyword…
The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively…
Recent applications of autonomous agents and robots, such as self-driving cars, scenario-based trainers, exploration robots, and service robots have brought attention to crucial trust-related challenges associated with the current…
How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…
Parameter identification for mechanistic Ordinary Differential Equation (ODE) models underpins prediction and control in several applications, yet remains a manual and labor-intensive process: datasets are noisy and partial, models can be…
As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment interaction. Existing agenticinfrastructure remain fragmented…
Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…
Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, yet public trust has not kept pace. The central reason is that responsibility, despite being widely discussed, remains a subjective and…
In this preprint, we present A collaborative human-AI approach to building an inspectable semantic layer for Agentic AI. AI agents first propose candidate knowledge structures from diverse data sources; domain experts then validate,…
Modern analytics systems are fundamentally reactive, requiring users to define queries over increasingly complex and continuously evolving data. In real-time streaming environments, this paradigm breaks down, as the space of potential…
The increasing complexity and scale of modern telecommunications networks demand intelligent automation to enhance efficiency, adaptability, and resilience. Agentic AI has emerged as a key paradigm for intelligent communications and…
Understandable and persuasive recommendations support the electricity consumers' behavioral change to tackle the energy efficiency problem. Generating load shifting recommendations for household appliances as explainable increases the…
We present the notion of explainability for decision-making processes in a pedagogically structured autonomous environment. Multi-agent systems that are structured pedagogically consist of pedagogical teachers and learners that operate in…
The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…
The field of machine learning has seen tremendous progress in recent years, with deep learning models delivering exceptional performance across a range of tasks. However, these models often come at the cost of interpretability, as they…
Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a fundamental constraint in real world teamwork, collaboration…
Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…
Modern agentic frameworks (e.g., CrewAI and AutoGen) have evolved into complex, autonomous multi-agent systems, introducing unique reliability challenges beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus…