Papers

Filtered to mechanistic discovery · clear filter

Browse by term

continual learning 91reinforcement learning 43vision-language models 18benchmarking 12benchmarks 11robotics 11large language models 10language models 9world models 9video generation 6generative models 5multimodal models 5natural language processing 5recursive self-improvement 5video world models 5agents 4dialogue systems 4diffusion models 4foundation models 4multimodal large language models 4on-policy distillation 4reasoning 4self-distillation 4self-supervised learning 4conversational AI 3evaluation benchmarks 3human-computer interaction 3LLMs 3multi-agent systems 3policy optimization 3

Matching papers

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

84 upvotes · 12 AUG 2026 · Mengru Wang, Junfeng Fang, Shuofei Qiao et al.

This paper introduces Mechanist, a system that uses AI to discover the underlying mechanisms of intelligence, allowing for better understanding and control of AI models. Practitioners might care because Mechanist can identify safety risks and improve model performance.

AImechanistic discoveryinterpretabilitycausal reasoningscientific instrumentationagent-based systems