AI
Recognizing Artificial Minds: A Philosophical Defense of AI Cognition
The authors argue that sophisticated Large Language Models (LLMs) like ChatGPT are full-blown lingui...
AI
SEISMO: Explanation-Aware, Trajectory-Conditioned LLM Agents for Sample-Efficient Molecular Optimisation
Researchers have developed a new AI system called SEISMO that can optimize molecules for specific pr...
AI
Can LLMs Introspect? A Reality Check
Researchers argue that recent studies claiming large language models (LLMs) can introspect and detec...
AI
GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
Researchers have developed GRASP (Gated Regression-Aware Skill Proposer), a method for self-improvin...
AI
Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight
Researchers have proposed a new approach to improving the performance of large l...
AI
Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
Researchers have developed a framework for agentic artificial intelligence that ...
AI
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
Researchers propose a new method called SafeSteer to align large language models...
AI
WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
WorldLines is a new benchmark for long-horizon stateful embodied agents. These a...