Researchers propose a new approach to scaling up the reasoning capabilities of large language models by using multiple agents that work together. This...
The authors argue that sophisticated Large Language Models (LLMs) like ChatGPT are full-blown linguistic and cognitive agents. They defend this positi...
Researchers have developed a new AI system called SEISMO that can optimize molecules for specific properties in a more efficient way than current meth...
Researchers argue that recent studies claiming large language models (LLMs) can introspect and detect their internal states may be premature. They pro...
Researchers have developed GRASP (Gated Regression-Aware Skill Proposer), a method for self-improving large language model (LLM) agents. GRASP treats ...
Researchers have proposed a new approach to improving the performance of large language models using weak critics. Instead of relying on strong labels...
Researchers have developed a framework for agentic artificial intelligence that enables scientific discovery through the revision of representational ...
Researchers propose a new method called SafeSteer to align large language models with human values without degrading their general capabilities. They ...
WorldLines is a new benchmark for long-horizon stateful embodied agents. These agents must remember user routines and past interactions to assist huma...
Researchers have developed a new AI system called AgRefactor that can automatically convert real-world software into code compatible with High-Level S...
Researchers have found that post-training quantization, a method used to compress large language models for deployment on resource-constrained devices...
Researchers have found that large language models can be vulnerable to 'jailbreaks' where seemingly safe instructions become unsafe when executed in t...