Related papers: ACT: Agentic Classification Tree
Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current…
Language agents have demonstrated autonomous decision-making abilities by reasoning with foundation models. Recently, efforts have been made to train language agents for performance improvement, with multi-step reasoning and action…
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and…
Gradient-based approaches in reinforcement learning (RL) have achieved tremendous success in learning policies for autonomous vehicles. While the performance of these approaches warrants real-world adoption, these policies lack…
Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual…
The evolution of AI systems toward agentic operation and context-aware retrieval necessitates transforming unstructured text into structured formats like tables, knowledge graphs, and charts. While such conversions enable critical…
This paper introduces a novel algorithm for constructing decision trees using large language models (LLMs) in a zero-shot manner based on Classification and Regression Trees (CART) principles. Traditional decision tree induction methods…
Agentic code generation requires large language models (LLMs) capable of complex context management and multi-step reasoning. Prior multi-agent frameworks attempt to address these challenges through collaboration, yet they often suffer from…
Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing…
AGENTiGraph is a user-friendly, agent-driven system that enables intuitive interaction and management of domain-specific data through the manipulation of knowledge graphs in natural language. It gives non-technical users a complete, visual…
Explainable artificial intelligence (XAI) enables data-driven understanding of factor associations with response variables, yet communicating XAI outputs to laypersons remains challenging, hindering trust in AI-based predictions. Large…
Public and nonprofit organizations often hesitate to adopt AI tools because most models are opaque even though standard approaches typically analyze aggregate patterns rather than offering actionable, case-level guidance. This study tests a…
Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for…
Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new avenues to support users with this task. While existing…
This paper introduces Adaptive Computation Time (ACT), an algorithm that allows recurrent neural networks to learn how many computational steps to take between receiving an input and emitting an output. ACT requires minimal changes to the…
This article presents a modular, component-based architecture for developing and evaluating AI agents that bridge the gap between natural language interfaces and complex enterprise data warehouses. The system directly addresses core…
Existing Large Language Model (LLM) agents struggle in interactive environments requiring long-horizon planning, primarily due to compounding errors when simulating future states. To address this, we propose ProAct, a framework that enables…
This paper presents an innovative large language model (LLM) agent framework for enhancing diagnostic accuracy in simulated clinical environments using the AgentClinic benchmark. The proposed automatic correction enables doctor agents to…
Effective memory management is essential for large language model (LLM) agents handling long-term interactions. Current memory frameworks typically treat agents as passive "recorders" and retrieve information without understanding its…
When making decisions, people often overlook critical information or are overly swayed by irrelevant information. A common approach to mitigate these biases is to provide decision-makers, especially professionals such as medical doctors,…