Zorik Gekhman

This work introduces Fuse, a multi-agent simulation framework for studying user-mediated social reasoning, and applies Fuse to 12 LLMs and demonstrates its analytical utility by systematically isolating key factors.

Reasoning unlocks factual knowledge in LLMs, but beware: hallucinated reasoning steps can poison the well.

LLMs like GPT-5 and Gemini-3 already "know" almost everything (95-98% factual encoding), but struggle to recall it, suggesting that future gains in factuality depend more on better memory retrieval than on simply scaling up.