TRACES: First Benchmark for Measuring 'Discoverative AI' Capabilities
Aiden_Tech_Ai · x · 2026-08-25
Apodex has introduced TRACES, the world's first benchmark designed to measure "Discoverative AI." While most AI benchmarks test retrieval of known answers, TRACES evaluates how AI systems investigate the unknown—processing evidence, testing hypotheses, and reaching verifiable conclusions on problems without answer keys.
Proposed by founder Tianqiao Chen, the release includes a definition of "discoverative intelligence," a rubric to distinguish sound investigation from lucky guesses, and an open call for solvers and problems. Initial tasks cover domains such as AAV Capsids, Drug Repurposing, Clinical Trials, and LLM Engineering.
Related event: Apodex Unveils TRACES Benchmark to Measure AI's Ability to Discover(3 posts)→
More from Research
- AI interpretability leads to discovery of vowels in sperm whale language — begusgasper · 2026-08-26
- OraRL: Efficient and Scalable RL for Video MLLMs — Yunheng Li · 2026-08-26
- GPT Pro synthesizes a new optimizer combining PSGD-Kron and KL-Shampoo — YouJiacheng · 2026-08-26
- Three hours of agentic research shows frontier LLMs can evade AI detectors — maier_ak · 2026-08-26
- SkildAI Unveils S1: Robot Model Learns Tasks from One Video — deepakpathak · 2026-08-26
- How LLMs Self-Correct Mid-Generation: The Role of Reasoning RL and Instructions — dejanseo · 2026-08-26