collaborators

6 papers

cs.AI2026

LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks

Po-Nien Kung, Linfeng Song, Dawsen Hwang +10

Large Language Models (LLMs) exhibit strong informal mathematical reasoning but struggle to generate mechanically verifiable proofs in formal languages like Lean. We present LEAP,…

cs.AI2026

Aletheia tackles FirstProof autonomously

Tony Feng, Junehyuk Jung, Sang-hyun Kim +14

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 t…

cs.LG20263 cited

Towards Autonomous Mathematics Research

Tony Feng, Trieu H. Trinh, Garrett Bingham +25

Recent advances in foundational models have yielded reasoning systems capable of achieving a gold-medal standard at the International Mathematical Olympiad. The transition from com…

cs.AI2026

Semi-Autonomous Mathematics Discovery with Gemini: A Case Study on the Erdős Problems

Tony Feng, Trieu Trinh, Garrett Bingham +21

We present a case study in semi-autonomous mathematics discovery, using Gemini to systematically evaluate 700 conjectures labeled 'Open' in Bloom's Erdős Problems database. We emp…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2025

Towards Robust Mathematical Reasoning

Thang Luong, Dawsen Hwang, Hoang H. Nguyen +17

Finding the right north-star metrics is highly critical for advancing the mathematical reasoning capabilities of foundation models, especially given that existing evaluations are e…