Apodex releases TRACES, the first benchmark for measuring 'discoverative AI' capabilities
aftahi_ai · x · 2026-08-23
Apodex has introduced TRACES, a new benchmark designed to evaluate 'discoverative intelligence'—the ability of AI to work through evidence, test hypotheses, and reach verifiable conclusions on problems without existing answer keys. Unlike benchmarks such as HLE or MMLU that measure retrieval of known answers, TRACES focuses on the process: using tools, fixing mistakes, and grounding conclusions. It has been applied to areas like rare-disease diagnosis, AAV gene delivery, and drug repurposing, asking whether a conclusion was actually earned rather than just guessed.
Related event: Apodex Launches TRACES Benchmark for AI Scientific Discovery(2 posts)→
More from Research
- Magnetic resonance force microscopy enables single-nm resolution imaging — zetalyrae · 2026-08-23
- Osaka Metro Univ AI replicates captain steering, follows unlearned rules — 4310sy · 2026-08-23
- Tsinghua Researchers Use GPT to Solve 40-Year-Old Optimization Problem — 新智元 · 2026-08-23
- RiO-DETR: First End-to-End Real-Time DETR for Oriented Object Detection — jiqizhixin · 2026-08-23
- Humanoid robotics shift toward end-to-end control for direct perception-driven movement — aftahi_ai · 2026-08-23
- Stanford/PKU paper: never train inside the world model — QWM uses it only for action selection — rohanpaul_ai · 2026-08-23