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
- False Collatz Proof via a Lean Bug: Talk Probes Proof Assistants as LLM-Found Bug Targets — marc_lelarge · 2026-10-16
- Goodfire's Nick Cammarata argues neural networks are 'already clean' in new interpretability essay — ctjlewis · 2026-10-16
- NEJM AI: prompt tuning cuts LLM clinical test-order cost ratio to 1.4x across 19 systems — dvir_a · 2026-10-16
- Prompting cuts LLM over-testing costs across 19 systems, but diagnosis agreement drops — dvir_a · 2026-10-16
- AI Recommends 3.2x Costlier Care; Models Add Tests in 2/3 of Visits Physicians Ordered None — dvir_a · 2026-10-16
- 24 AI Systems Recommend $314 Per Visit in Care vs Physicians' $97, a 3.2x Gap — dvir_a · 2026-10-16