Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence

2026-08-11

AI Summary

Current AI systems struggle to achieve verifiable discoveries in real-world, complex tasks characterized by ambiguous problem formulations and ill-defined tools or success criteria. This work proposes the Apodex Discovery framework, which integrates foundation models, toolchains, and control strategies into a reconfigurable solver to enable traceable, verifiable long-horizon exploration within structured environments. The framework introduces TRACES—a novel task-environment abstraction—and the HDS6 six-dimensional evaluation metric (Tool usage, Repair, Alternatives, Coherence, Evidence, and Scope)—to support fine-grained attribution analysis of the discovery process. Empirical results demonstrate that Apodex outperforms state-of-the-art methods by 7% in AAV capsid design and significantly enhances prediction scores for GPT-5.5 and GPT-5.6-sol by 2.5 and 7.6 points, respectively, in drug repurposing tasks.

Abstract

Apollo did not reach the Moon merely because its engineers could solve difficult equations. It succeeded by turning a distant ambition into a mission architecture of explicit objectives, simulation, verification, and repeated correction. AI now faces a similar transition: frontier models can solve difficult tasks once the problem, tools, and success criteria are specified, yet consequential real-world challenges rarely arrive in an executable or verifiable form. We introduce Apodex Discovery, a framework for building and evaluating discoverative AI through the heavy-duty solver, a system comprising a foundation model, harness, tools, and control policies that pursues extended, stateful, verifiable investigations. It has three core components. First, a problem-scouting process surveyed 561 industries across 16 sectors, assembled 423 high-value real-world problems, and selected 20 for the initial release. Second, a common environment-task-episode abstraction provides data, tools, constraints, feedback, trajectory recording, and verification of intermediate artifacts and final submissions. Third, HDS6 evaluates Tools, Repair, Alternatives, Coherence, Evidence, and Scope independently of final-task success. In AAV capsid design, Apodex surpassed the published state of the art by 7% across viability, tropism, structure prediction, and generative design. In drug repurposing and reformulation, a task-specific biomedical environment improved the mean normalized prediction score of GPT-5.5 and GPT-5.6-sol by 2.5 and 7.6 points over the same closed-book backbone. Controlled ablations show that the fixed TRACES episode interface enables attribution of performance differences to specific solver components. Apodex Discovery moves AI evaluation beyond predefined benchmarks toward verifiable investigations aimed at genuine discovery.

Problem

• discoverative AI
• real-world problems
• verifiable investigations
• AI evaluation
• mission architecture

Innovation

• discoverative AI
• verifiable investigation
• HDS6 evaluation
• problem-scouting
• environment-task-episode abstraction