Related papers: CORPGEN: Simulating Corporate Environments with Au…
Given an increasing prevalence of intelligent systems capable of autonomous actions or augmenting human activities, it is important to consider scenarios in which the human, autonomous system, or both can exhibit failures as a result of one…
LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly integrating these capabilities into unified systems. Yet, most…
Deep learning systems are optimized for clusters with homogeneous resources. However, heterogeneity is prevalent in computing infrastructure across edge, cloud and HPC. When training neural networks using stochastic gradient descent…
Progress in computer use agents (CUAs) has been constrained by the absence of large and high-quality datasets that capture how humans interact with a computer. While LLMs have thrived on abundant textual data, no comparable corpus exists…
Reconstructing past events requires reasoning across long time horizons. To figure out what happened, we need to use our prior knowledge about the world and human behavior and draw inferences from various sources of evidence including…
LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. While prior benchmarks evaluate only single-entity updates, MEME defines six tasks spanning…
Long-horizon embodied planning underpins embodied AI. To accomplish long-horizon tasks, one of the most feasible ways is to decompose abstract instructions into a sequence of actionable steps. Foundation models still face logical errors and…
We present C-Procgen, an enhanced suite of environments on top of the Procgen benchmark. C-Procgen provides access to over 200 unique game contexts across 16 games. It allows for detailed configuration of environments, ranging from game…
While the advancement of large language models has spurred the development of AI agents to automate tasks, numerous use cases inherently require agents to collaborate with humans due to humans' latent preferences, domain expertise, or the…
This paper extends the paradigm of "mobile edge learning (MEL)" by designing an optimal task allocation scheme for training a machine learning model in an asynchronous manner across mutiple edge nodes or learners connected via a…
We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve long-horizon tasks in domains with multiple entities.…
Domain-specific systems-on-chip, a class of heterogeneous many-core systems, are recognized as a key approach to narrow down the performance and energy-efficiency gap between custom hardware accelerators and programmable processors.…
The quality of AI-generated output is often attributed to prompting technique, but extensive empirical observation suggests that context completeness may be more strongly associated with output quality. This paper introduces Context…
We investigate in-context learning (ICL) through a meticulous experimental framework that systematically varies task complexity and model architecture. Extending beyond the linear regression baseline, we introduce Gaussian kernel regression…
Effective asynchronous planning, or the ability to efficiently reason and plan over states and actions that must happen in parallel or sequentially, is essential for agents that must account for time delays, reason over diverse long-horizon…
The Computing Continuum (CC) integrates different layers of processing infrastructure, from Edge to Cloud, to optimize service quality through ubiquitous and reliable computation. Compared to central architectures, however, heterogeneous…
Healthcare administration accounts for over $1 trillion in annual spending, making it a promising target for LLM-based computer-use agents (CUAs). While clinical applications of LLMs have received significant attention, no benchmark exists…
The next generation of autonomous AI systems will be constrained not only by model capability, but by how intelligence is structured across heterogeneous hardware. Current paradigms -- cloud-centric AI, on-device inference, and edge-cloud…
We present the COGnitive Neural GENerative system (CogNGen), a cognitive architecture that combines two neurobiologically-plausible, computational models: predictive processing and hyperdimensional/vector-symbolic models. We draw…
Mobile agents show immense potential, yet current state-of-the-art (SoTA) agents exhibit inadequate success rates on real-world, long-horizon, cross-application tasks. We attribute this bottleneck to the agents' excessive reliance on…