UIUC releases OpenFrontiers: open research problems corpus plus scientific rediscovery benchmark for LLM agents
Jiarui Yao · hf · 2026-11-07
Researchers at UIUC (Jiarui Yao, Ruida Wang, Tong Zhang) introduce OpenFrontiers, a cross-disciplinary resource for evaluating LLM agents on research-level problems.
- An open research problems corpus recording problem statements, context, and progress across disciplines.
- A formally graded retrospective benchmark of recently resolved mathematics problems, testing whether agents can rediscover solutions under varying information-access conditions.
- The paper argues open-problem evaluation is harder than exam-style benchmarks (FrontierMath, Humanity's Last Exam, GPQA), which saturate quickly and leak into training data.
arXiv, 27 Oct 2026.
More from Research
- Regularization can amplify subliminal learning, surprising AI safety finding — AdtRaghunathan · 2026-11-07
- OpenVax revamps personalized cancer vaccine toolkit; OpenVax2 adds long-read support — iskander · 2026-11-07
- Google's Muir linear attention fits 10M tokens in a 25MB state, beats GDN-2 — CategoryNormal149 · 2026-11-07
- OpenAI launches BioBasicsBench: 100 real wet-lab tasks to stress-test AI agents — OpenAI · 2026-11-07
- Scaling systolic array diagrams from 8x8 to 64x64: 4096 PE matrix multiply visualized — satnam6502 · 2026-11-07
- Aristotle formally verifies FP16 systolic matrix multipliers up to 64x64 in Lean 4 — satnam6502 · 2026-11-07