Apodex Launches TRACES, First Benchmark for Evaluating 'Discoverative AI' on Real-World Problems
Faheem_uh · x · 2026-09-11
Apodex released Apodex Discovery, a new benchmark paradigm for 'discoverative AI' — targeting real-world problems with no ground truth answers. Key points:
- TRACES is the first published standard evaluating the likelihood of defensible discovery when the answer is unknown.
- The evaluation unit is the complete solver: model, tools, memory, and workflow together.
- Built from fieldwork by 10 STEM PhDs scouting 561 industries across 16 sectors, yielding a registry of 423 real-world problems; 20 are live as executable environments (AAV gene-delivery design, drug repurposing, clinical trials, LLM engineering).
- Problem and solver submissions are open; paper is on Hugging Face.
Related event: Apodex unveils TRACES benchmark for discovery-oriented AI(3 posts)→
More from Research
- Fortnow: P vs NP beyond AI's reach, but NP vs L separations could fall — fortnow · 2026-09-11
- MaP-WAM tackles non-Markovian robot manipulation with memory-grounded planning — Sizhe Zhao · 2026-09-11
- Negative Self-Distillation improves LLM reasoning by avoiding flawed reasoning paths — Rongcan Pei · 2026-09-11
- DeepMind-led paper makes design docs the source of truth, code disposable — SMART regenerates in 1.5-3h for ~$100 — Roger_M_Taylor · 2026-09-11
- GameWorld wins Best Paper Runner-Up at ECCV 2026 Multimodal Digital Agents Workshop — MikeShou1 · 2026-09-11
- Yann LeCun live at ECCV on World Models — Weak_Assistance_5261 · 2026-09-11