Environments give AI eyes to see, hands to act, and a world to solve.

Apodex Discovery turns real-world problems into executable environments where AI can observe, act, use tools, receive feedback, and prove what it can actually do.

We collectively refer to our real-world problems, environments, and scoring systems as the TRACES benchmark.

We are releasing a selection of TRACES problems and environments for the community to explore — including their data, tools, and how verification works.

These are only a glimpse of the full TRACES benchmark, chosen to make our approach concrete and accessible while the broader collection continues to grow.

Case study · measured result · beats human SOTA

Rare disease diagnosis — built autonomously by AI in 12 hours

From one sentence of task description — zero data, zero human intervention — the system found its own cases, built its own knowledge base and tools, trained its own models, and delivered a complete offline diagnostic system that beats the human state of the art published in Nature (Recall@1 0.678 vs 0.628) on 556 held-out cases.

4 tasks · 18 episodes

Adeno-associated virus (AAV) capsid design

A four-stage gene-delivery pipeline: predict whether a capsid variant is viable, predict its tropism, reconstruct its 3-D structure, and generate novel manufacturable sequences under a limited experimental-feedback budget.

1 task · 100 public + 200 hidden episodes

Drug repurposing & reformulation

Drug repurposing and reformulation (DRR) does not aim to discover new drugs. Instead, it seeks to identify new therapeutic indications and optimized procedure design for existing approved or clinically characterized drugs.

2 tasks · 100 episodes

Clinical trials

Statistical analysis and reporting under a pre-specified analysis plan, safety- and efficacy-signal discovery, and forecasting whether a program advances to its next phase.

11 tasks · 102 episodes

LLM data, training & systems

The stack that builds the model: corpus procurement, filtering, deduplication and benchmark construction, plus recipe discovery, determinism repair, distributed-training debugging and verifier authoring.

Highlight · Adeno-associated virus (AAV) capsid engineering

See how TRACES helped Apodex beat published SOTA on designing the viral shells that deliver gene therapies

Inside the AAV environment, frontier systems clear the published state of the art at all four stages — viability, tropism, structure, and de novo design. Apodex model-generated capsids are in preclinical laboratory testing; no human data.

“The true AGI benchmark of the future should not be a benchmark at all. It should be a Reality Benchmark — not a dataset, but an entire runnable world.”
Mr. Tianqiao Chen, Founder & CEO of Apodex