Researchers have been studying how large language models (LLMs) can collaborate to solve complex problems. They tested four different collaboration pr...
Researchers have developed a method to identify the optimal order in which large models should resolve skill bottlenecks during training. They propose...
Researchers have proposed a new approach to evaluating AI agents, addressing issues with outcome finality and cross-unit separation in current evaluat...
Researchers compared four methods for loading agent skills in AI systems: pre-loading all skills at once, loading only what's needed, progressive disc...
Researchers have developed a new method for on-policy self-distillation in agentic reinforcement learning. The approach, called Influence Calibration ...
Researchers have developed a method called RETRACE to estimate opioid craving from wearable physiological signals. The approach uses psychological res...
Researchers have developed a new compiler framework called T-LLM Compiler that uses large language models (LLMs) to optimize and verify code. The fram...
Researchers have developed a framework to design on-demand Urban Air Mobility (UAM) networks that balance vertiport siting and fleet simulation. The a...
Researchers tested whether using a tool's results in a synthetic assignment task affects a language model's answer. They found that when a tool result...
Researchers have proposed a new framework called S2-MoE to improve the efficiency of large language models on edge devices. These devices are limited ...
Researchers have made progress in understanding how language models process information. They found that attention mechanisms play a crucial role in t...
Researchers have developed a framework for coordinating multiple interacting units in complex systems. The approach uses a large language model (LLM) ...