AI resolves 100+ of 244 open research problems; proofs withheld to avoid contamination
wellecks · x · 2026-10-20
The REUF2F benchmark team reveals models resolved over 100 of 244 open research problems, but the proofs will not be released — withholding benchmark solutions is good practice to mitigate contamination.
A key feature: models can either prove or disprove a problem's statement, rather than producing a single canonical answer.
More from Research
- Position paper: humans are missing from AI coding agent research — math_rachel · 2026-10-20
- Hazy Research's open-source NCM generates text 31x faster via coarse-to-fine concept modeling — simran_s_arora · 2026-10-20
- New scaling-law paper argues data curation cannot be compute-agnostic: repeated high-quality data loses utility fast — cwolferesearch · 2026-10-20
- RuneBench: Benchmarking AI Coding Agents by Playing RuneScape — charliermarsh · 2026-10-20
- FOMO-Dex uses force-aware Sharpa glove to make screwdriving teleoperable, questioning sim-to-real necessity — HaozhiQ · 2026-10-20
- Blog: recursive self-improvement and AI scientists for semi-well-defined problems — rishabh16_ · 2026-10-20