Related papers: From Experience to Skill: Multi-Agent Generative E…

There are two common approaches for optimizing the performance of a machine: genetic algorithms and machine learning. A genetic algorithm is applied over many generations whereas machine learning works by applying feedback until the system…

Generative models have gained significant traction in offline reinforcement learning (RL) due to their ability to model complex trajectory distributions. However, existing generation-based approaches still struggle with long-horizon tasks…

Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete…

Retrieval-augmented generation (RAG) has become a cornerstone for knowledge-intensive tasks. However, the efficacy of RAG is often bottlenecked by the ``one-size-fits-all'' retrieval paradigm, as different queries exhibit distinct…

Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some…

Searching for accurate Machine and Deep Learning models is a computationally expensive and awfully energivorous process. A strategy which has been gaining recently importance to drastically reduce computational time and energy consumed is…

Evaluating multi-turn interactive agents is challenging due to the need for human assessment. Evaluation with simulated users has been introduced as an alternative, however existing approaches typically model generic users and overlook the…

Automated scoring of written constructed responses typically relies on separate models per task, straining computational resources, storage, and maintenance in real-world education settings. We propose UniMoE-Guided, a knowledge-distilled…

The evolution of Retrieval-Augmented Generation (RAG) has shifted from static retrieval pipelines to dynamic, agentic workflows where a central planner orchestrates multi-turn reasoning. However, existing paradigms face a critical…

In a multi-stage recommendation system, reranking plays a crucial role in modeling intra-list correlations among items. A key challenge lies in exploring optimal sequences within the combinatorial space of permutations. Recent research…

Generative models often incur the catastrophic forgetting problem when they are used to sequentially learning multiple tasks, i.e., lifelong generative learning. Although there are some endeavors to tackle this problem, they suffer from…

When applying Bayesian optimization (BO) to scientific workflow, a major yet often overlooked source of uncertainty is the task itself -- namely, what to optimize and how to evaluate it -- which can evolve as evidence accumulates. We…

We present GELATO -- the first language-driven trajectory reshaping framework to embed geometric environment awareness and multi-agent feedback orchestration to support multi-instruction in human-robot interaction scenarios. Unlike prior…

The field of meta-learning seeks to improve the ability of today's machine learning systems to adapt efficiently to small amounts of data. Typically this is accomplished by training a system with a parametrized update rule to improve a…

Generative Adversarial Networks (GANs) have achieved remarkable results in the task of generating realistic natural images. In most successful applications, GAN models share two common aspects: solving a challenging saddle point…

Engineering design optimization requires an efficient combination of a 3D shape representation, an optimization algorithm, and a design performance evaluation method, which is often computationally expensive. We present a prompt evolution…

Multi-agent reinforcement learning (MARL) algorithms have accomplished remarkable breakthroughs in solving large-scale decision-making tasks. Nonetheless, most existing MARL algorithms are model-free, limiting sample efficiency and…

In this paper, we study the generative models of sequential discrete data. To tackle the exposure bias problem inherent in maximum likelihood estimation (MLE), generative adversarial networks (GANs) are introduced to penalize the…

Autonomous research agents can already run machine learning experiments without human supervision, but many rely on a narrow search strategy: they repeatedly modify one program and keep changes only when they improve the current best…

Multi-agent reinforcement learning faces fundamental challenges that conventional approaches have failed to overcome: exponentially growing joint action spaces, non-stationary environments where simultaneous learning creates moving targets,…