Related papers: Position: Beyond Model-Centric Prediction -- Agent…

Agentic frameworks powered by Large Language Models (LLMs) can be useful tools in scientific workflows by enabling human-AI co-creation. A key challenge is recommending the next steps during workflow creation without relying solely on LLMs,…

Transformer-based architectures have achieved remarkable success in natural language processing and computer vision. However, their performance in multivariate long-term forecasting often falls short compared to simpler linear baselines.…

Recent years have witnessed substantial growth in adaptive traffic signal control (ATSC) methodologies that improve transportation network efficiency, especially in branches leveraging artificial intelligence based optimization and control…

The multi-agent pathfinding (MAPF) problem seeks collision-free paths for a team of agents from their current positions to their pre-set goals in a known environment, and is an essential problem found at the core of many logistics,…

Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior…

We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data, such as irregular samples, missing data, or unaligned measurements from multiple…

Future trajectories of neighboring traffic agents have a significant influence on the path planning and decision-making of autonomous vehicles. While trajectory forecasting is a well-studied field, research mainly focuses on snapshot-based…

As comprehensive large model evaluation becomes prohibitively expensive, predicting model performance from limited observations has become essential. However, existing statistical methods struggle with pattern shifts, data sparsity, and…

Time series forecasting is critical to real-world decision making, yet most existing approaches remain unimodal and rely on extrapolating historical patterns. While recent progress in large language models (LLMs) highlights the potential…

In contemporary data-driven environments, the generation and processing of multivariate time series data is an omnipresent challenge, often complicated by time delays between different time series. These delays, originating from a multitude…

With the rapid development of LLM-based agents, there is a growing trend to incorporate agent-specific data into the pre-training stage of LLMs, aiming to better align LLMs with real-world autonomous task execution. However, current…

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…

Evaluating the contribution of individual data points to a model's prediction is critical for interpreting model predictions and improving model performance. Existing data contribution methods have been applied to various data types,…

Artificial intelligence is undergoing a structural transformation marked by the rise of agentic systems capable of open-ended action trajectories, generative representations and outputs, and evolving objectives. These properties introduce…

The emergence of large language models has catalyzed two distinct yet interconnected paradigms in artificial intelligence: standalone AI Agents and collaborative Agentic AI ecosystems. This comprehensive study establishes a definitive…

Despite the extensive use of the agent technology in the Supply Chain Management field, its integration with Advanced Planning and Scheduling (APS) tools still represents a promising field with several open research questions. Specifically,…

There has been a recent surge of interest in time series modeling using the Transformer architecture. However, forecasting multivariate time series with Transformer presents a unique challenge as it requires modeling both temporal…

Time series forecasting (TSF) plays a crucial role in many applications. Transformer-based methods are one of the mainstream techniques for TSF. Existing methods treat all token dependencies equally. However, we find that the effectiveness…

Non-stationarity is an intrinsic property of real-world time series and plays a crucial role in time series forecasting. Previous studies primarily adopt instance normalization to attenuate the non-stationarity of original series for better…

Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensive. Scaling RL to agentic LLMs requires supporting complex…