Lessons from Studying Two-Hop Latent Reasoning

Understand

Large language models can use chain-of-thought (CoT) to externalize reasoning, potentially enabling oversight of capable LLM agents.

• Prior work has shown that models struggle at two-hop question-answering without CoT.
• This capability is so basic that if it was a fundamental limitation, it would imply that many complex agentic tasks would similarly require CoT.
• We investigate LLM latent reasoning capabilities using two-hop question answering as a case study.