Aletheia tackles FirstProof autonomously
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ProofCouncil: An LLM Agent for Solving Open Mathematical Problems
Large language models (LLMs) have shown increasing promise in solving open problems in mathematics. However, their performance can be further improved through agentic workflows tailored to real-world mathematical practic…
Verify as You Go: An LLM-Powered Browser Extension for Fake News Detection
The rampant spread of fake news in the digital age poses serious risks to public trust and democratic institutions, underscoring the need for effective, transparent, and user-centered detection tools. Existing browser ex…
Fake News DetectionTowards Autonomous Mathematics Research
Recent advances in foundational models have yielded reasoning systems capable of achieving a gold-medal standard at the International Mathematical Olympiad. The transition from competition-level problem-solving to profes…
Aletheia: Gradient-Guided Layer Selection for Efficient LoRA Fine-Tuning Across Architectures
Low-Rank Adaptation (LoRA) has become the dominant parameter-efficient fine-tuning method for large language models, yet standard practice applies LoRA adapters uniformly to all transformer layers regardless of their rel…
parameter-efficient fine-tuningAletheia: An Offline-First Clinical Decision Support System for Differential Diagnosis in Low-Resource Healthcare Settings
Access to specialist clinical expertise remains severely limited across sub-Saharan Africa, where physician-to-patient ratios can fall below 1:25,000 in rural settings. Existing AI-assisted diagnostic tools predominantly…