AI agents have become proficient at following a pre-defined strategy to execute tasks. The next major frontier, and a significant bottleneck, is the ability to explore open-ended environments and generate novel strategies independently. This is the core capability that benchmarks like ARC AGI v3 are designed to test.

AI struggles with long-horizon tasks not just due to technical limits, but because we lack good ways to measure performance. Once effective evaluations (evals) for these capabilities exist, researchers can rapidly optimize models against them, accelerating progress significantly.

Issues like 'saturation' and 'maxing' reveal a fundamental flaw: benchmarks test narrow, siloed abilities ('Task AGI'). They fail to measure an AI's capacity to combine skills to solve multi-step problems, which is the true bottleneck preventing real-world agentic performance and the next frontier of AI.

The frontier of AI training is moving beyond humans ranking model outputs (RLHF). Now, high-skilled experts create detailed success criteria (like rubrics or unit tests), which an AI then uses to provide feedback to the main model at scale, a process called RLAIF.

Building a functional AI agent is just the starting point. The real work lies in developing a set of evaluations ("evals") to test if the agent consistently behaves as expected. Without quantifying failures and successes against a standard, you're just guessing, not iteratively improving the agent's performance.

The latest Arc AGI benchmark ditches static puzzles for interactive games with no instructions. This forces models to explore, learn rules, and adapt on the fly. It directly measures their ability to acquire new skills efficiently—a closer proxy for general intelligence than testing memorized reasoning patterns.

Traditional AI benchmarks are seen as increasingly incremental and less interesting. The new frontier for evaluating a model's true capability lies in applied, complex tasks that mimic real-world interaction, such as building in Minecraft (MC Bench) or managing a simulated business (VendingBench), which are more revealing of raw intelligence.

As reinforcement learning (RL) techniques mature, the core challenge shifts from the algorithm to the problem definition. The competitive moat for AI companies will be their ability to create high-fidelity environments and benchmarks that accurately represent complex, real-world tasks, effectively teaching the AI what matters.

Platforms like Trajectory RL are creating marketplaces for AI "skills" — applications written in plain text, not code. This signals a paradigm shift where the next software layer for AI agents will be built on natural language instructions rather than traditional programming.