research note
This paper addresses the challenge of efficiently training and scaling Multi-Agent Systems (MAS) built on Large Language Models (LLMs), where orchestration of specialized agents is key to task perf…
research note
RoboProcessBench addresses the critical gap in evaluating whether vision-language models (VLMs) possess fine-grained process-aware understanding necessary for robotic manipulation tasks
research note
This paper presents the first search for high-frequency gravitational waves (HFGWs) in the 1 GHz to 1 THz range using geomagnetic conversion detected by radio telescopes
research note
This paper addresses efficient and faithful communication among heterogeneous large language model (LLM) agents in multi-agent systems (MAS)
research note
This paper addresses the problem of certifying nonlocality without entanglement (NLWE) in practical quantum measurement scenarios where devices may be untrusted and suffer from imperfections such a…
research note
This paper addresses the core challenge of open-ended spatial reasoning in vision-language models (VLMs), specifically how the design of an agent's action interface impacts its ability to compose c…
research note
This paper addresses the longstanding challenge in photoelectrochemical oxygen evolution reaction (OER), which is hindered not only by kinetic barriers but also by spin constraints linked to formin…
research note
This paper addresses a fundamental question in modeling user behavior on social web highlighters — whether a reader's document selection signature represents a stable "trait" or a transient "state."…
research note
This work addresses the challenge of simultaneously achieving ultra-low magnetic damping, perpendicular magnetic anisotropy (PMA), and low spin-orbit torque (SOT) switching current densities in ult…
research note
This paper addresses the fundamental challenge of performing statistically valid inference when only synthetic data are available for a target scientific task
research note
VietFashion addresses the challenge of fine-grained, culturally grounded sketch-text composed image retrieval (ST-CIR) specifically for traditional Vietnamese Ao Dai garments
research note
This paper addresses a crucial but under-explored aspect of prompt injection attacks on large language model (LLM)-driven web agents — the asymmetric and stakeholder-dependent nature of harm in real…
