Aletheia tackles FirstProof autonomously
This demonstrates progress in autonomous theorem-proving for mathematics research, though it is incremental as it builds on existing AI models.
Aletheia, a mathematics research agent, tackled the FirstProof challenge by autonomously solving 6 out of 10 problems within the allowed timeframe, with expert assessments confirming most solutions.
We report the performance of Aletheia (Feng et al., 2026b), a mathematics research agent powered by Gemini 3 Deep Think, on the inaugural FirstProof challenge. Within the allowed timeframe of the challenge, Aletheia autonomously solved 6 problems (2, 5, 7, 8, 9, 10) out of 10 according to majority expert assessments; we note that experts were not unanimous on Problem 8 (only). For full transparency, we explain our interpretation of FirstProof and disclose details about our experiments as well as our evaluation. Raw prompts and outputs are available at https://github.com/google-deepmind/superhuman/tree/main/aletheia.