Related papers: Reactive Message Passing for Scalable Bayesian Inf…

We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs) inspired by human meta-reasoning. Traditional in-context learning-based reasoning techniques, such as…

Multi-step planning has been widely employed to enhance the performance of large language models (LLMs) on downstream natural language processing (NLP) tasks, which decomposes the original task into multiple subtasks and guide LLMs to solve…

The envelope model provides a dimension-reduction framework for multivariate linear regression. However, existing envelope methods typically assume normally distributed random errors and do not accommodate repeated measures in longitudinal…

Reconfigurable intelligent surface (RIS) has emerged as a promising technique for future wireless communication networks. How to reliably transmit information in a RIS-based communication system arouses much interest. This paper proposes a…

Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using…

Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling principle from a single model to multi-agent…

Sequential sampling models (SSMs) are a widely used framework describing decision-making as a stochastic, dynamic process of evidence accumulation. SSMs popularity across cognitive science has driven the development of various software…

Many complex processes can be viewed as dynamical systems of interacting agents. In many cases, only the state sequences of individual agents are observed, while the interacting relations and the dynamical rules are unknown. The neural…

In this work, we discover that causal inference provides a promising approach to capture heterophilic message-passing in Graph Neural Network (GNN). By leveraging cause-effect analysis, we can discern heterophilic edges based on asymmetric…

Recent scene graph generation (SGG) frameworks have focused on learning complex relationships among multiple objects in an image. Thanks to the nature of the message passing neural network (MPNN) that models high-order interactions between…

Reducing hallucination of Large Language Models (LLMs) is imperative for use in the sciences, where reliability and reproducibility are crucial. However, LLMs inherently lack long-term memory, making it a nontrivial, ad hoc, and inevitably…

Planning under model uncertainty is a fundamental problem across many applications of decision making and learning. In this paper, we propose the Robust Adaptive Monte Carlo Planning (RAMCP) algorithm, which allows computation of…

Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct)…

Reactive languages are dedicated to the programming of systems which interact continuously and concurrently with their environment. Values take the form of unbounded streams modeling the (discrete) passing of time or the sequence of…

Message passing is the core of most graph models such as Graph Convolutional Network (GCN) and Label Propagation (LP), which usually require a large number of clean labeled data to smooth out the neighborhood over the graph. However, the…

How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative latent-state refinement with shared…

Although the Bayesian paradigm offers a formal framework for estimating the entire probability distribution over uncertain parameters, its online implementation can be challenging due to high computational costs. We suggest the Adaptive…

Adaptive Informative Path Planning with Multimodal Sensing (AIPPMS) considers the problem of an agent equipped with multiple sensors, each with different sensing accuracy and energy costs. The agent's goal is to explore the environment and…

Approximate message passing (AMP) is a scalable, iterative approach to signal recovery. For structured random measurement ensembles, including independent and identically distributed (i.i.d.) Gaussian and rotationally-invariant matrices,…

Temporal point process (TPP) models combined with recurrent neural networks provide a powerful framework for modeling continuous-time event data. While such models are flexible, they are inherently sequential and therefore cannot benefit…