相关论文: Scaling Laws for Agent Harnesses via Effective Fee…

Learning and predicting the performance of a configurable software system helps to provide better quality assurance. One important engineering decision therein is how to encode the configuration into the model built. Despite the presence of…

Language models are increasingly used in scientific discovery to generate hypotheses, propose candidate solutions, implement systems, and iteratively refine them. At the core of these trial-and-error loops lies evaluation: the process of…

Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of…

Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform…

Traditional model-free feature selection methods treat each feature independently while disregarding the interrelationships among features, which leads to relatively poor performance compared with the model-aware methods. To address this…

As large language models (LLMs) become increasingly versatile, numerous large scale benchmarks have been developed to thoroughly assess their capabilities. These benchmarks typically consist of diverse datasets and prompts to evaluate…

In an interactive error-correcting code (iECC), Alice and Bob engage in an interactive protocol with the goal of Alice communicating a message $x \in \{ 0, 1 \}^k$ to Bob in such a way that even if some fraction of the total communicated…

Foundation models for structured electronic health records (EHRs) are pretrained on longitudinal sequences of timestamped clinical events to learn adaptable patient representations. Tokenization -- how these timelines are converted into…

We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of…

Language model agents often appear capable of self-recovery after failing tool call executions, yet this behavior lacks a formal explanation. We present a predictive theory that resolves this gap by showing that recoverability follows a…

The consensus strategies used in collaborative multi-agent systems (MAS) face notable challenges related to adaptability, scalability, and convergence certainties. These approaches, including structured workflows, debate models, and…

While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this…

Voice agents, artificial intelligence systems that conduct spoken conversations to complete tasks, are increasingly deployed across enterprise applications. However, no existing benchmark jointly addresses two core evaluation challenges:…

Formative feedback is widely recognized as one of the most effective drivers of student learning, yet it remains difficult to implement equitably at scale. In large or low-resource courses, instructors often lack the time, staffing, and…

Hawkes process provides an effective statistical framework for analyzing the time-dependent interaction of neuronal spiking activities. Although utilized in many real applications, the classic Hawkes process is incapable of modelling…

Model routing chooses which language model to use for each query. By sending easy queries to cheaper models and hard queries to stronger ones, it can significantly reduce inference cost while maintaining high accuracy. However, most…

HPC systems expose many configuration parameters that jointly drive competing objectives. Existing tools such as autotuners recommend good configurations but do not identify minimal changes for a near-miss configuration to meet a…

Agent harnesses -- the stateful programs that wrap a language model and decide what it sees at each step -- are now known to change end-to-end performance on a fixed model by as much as six times. That raises a question asked less often…

To improve customer experience, datacenter operators offer support for simplifying application and resource management. For example, running workloads of workflows on behalf of customers is desirable, but requires increasingly more…

Current agentic AI benchmarks predominantly evaluate task completion accuracy, while overlooking critical enterprise requirements such as cost-efficiency, reliability, and operational stability. Through systematic analysis of 12 main…