Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards. Recent RLVR works that operate under the zero setting avoid supervision in labeling the reasoning process, but still depend on manually curated collections of questions and answers for training. The scarcity of highquality, human-produced examples raises concerns about the long-term scalability of relying on human supervision, a challenge already evident in the domain of language model pretraining. Furthermore, in a hypothetical future where AI surpasses human intelligence, tasks provided by humans may offer limited learning potential for a superintelligent system. To address these concerns, we propose a new RLVR paradigm called Absolute Zero, in which a single model learns to propose tasks that maximize its own learning progress and improves reasoning by solving them, without relying on any external data. Under this paradigm, we introduce the Absolute Zero Reasoner (AZR), a system that self-evolves its training curriculum and reasoning ability by using a code executor to both validate proposed code reasoning tasks and verify answers, serving as an unified source of verifiable reward to guide open-ended yet grounded learning. Despite being trained entirely without external data, AZR achieves overall SOTA performance on coding

A particularly compelling variant is the “zero” RLVR paradigm (DeepSeek-AI et al., 2025), which forgoes any cold-start distillation data, using neither human-generated nor AI-generated reasoning traces, and applies RLVR directly on the base model with task rewards. However, these methods still depend heavily on expertly curated distributions of reasoning question–answer pairs, which raises serious concerns about their long-term scalability (Villalobos et al., 2024). As reasoning models continue to advance, the effort required to construct large-scale, high-quality datasets may soon become unsustainable (Yue et al., 2025). A similar scalability bottleneck has already been identified in the domain of LLM pretraining (Sutskever et al., 2024). Furthermore, as AI systems continue to evolve and potentially exceed human intellect, an exclusive dependence on human-designed tasks risks imposing constraints on their capacity for autonomous learning and growth (Hughes et al., 2024).

To this end, we propose “Absolute Zero”, a new paradigm for reasoning models in which the model simultaneously learns to define tasks that maximize learnability and to solve them effectively, enabling self-evolution through self-play without relying on external data. In contrast to prior self-play methods that are limited to narrow domains, fixed functionalities, or learned reward models that are prone to hacking (Silver et al., 2017; Chen et al., 2025; 2024), the Absolute Zero paradigm is designed to operate in open-ended settings while remaining grounded in a real environment. It relies on feedback from the environment as a verifiable source of reward, mirroring how humans learn and reason through interaction with the world, and helps prevent issues such as hacking with neural reward models (Hughes et al., 2024).

We let AZR construct three types of coding tasks: infer and reason about one particular element in a program, input, output triplet, which corresponds to three complementary modes of reasoning: induction, abduction, and deduction. We train the entire system end-to-end with a newly proposed reinforcement learning advantage estimator tailored to the multitask nature of the proposed approach.

In coding tasks, AZR establishes a new state-of-the-art performance, surpassing models specifically trained with code datasets using RLVR. Furthermore, AZR outperforms all previous models by an average of 1.8 absolute points compared to models trained in the “zero” setting using in-domain data. These surprising results highlight that general reasoning skills can emerge without human-curated domain targeted data, positioning Absolute Zero as an promising research direction and AZR as a first pivotal milestone.

Cognitive Behaviors and Token length depends on reasoning mode. Distinct cognitive behaviors—such as step-by-step reasoning, enumeration, and trial-and-error all emerged through AZR training, but different behaviors are particularly evident across different types of tasks. Furthermore token counts grow over AZR training, but the magnitude of increase also differs by task types: abduction grows the most because the model performs trial-and-error until output matches, whereas deduction and induction grow modestly.

Large language models are naturally suited for implementing AZR in a multitask learning context (Radford et al., 2019), as both the formulation of reasoning tasks and their solutions occur within a unified language space. To this end, we propose rewarding a single model for both generating high learning potential tasks and solving them effectively, as specified by the Absolute Zero objective in Equation (3). At each iteration of the online rollout, AZR proposes new reasoning tasks by conditioning on the task type (as defined in Section 3.2) and K past self-generated examples. The model is explicitly prompted to generate tasks that differ from these examples, promoting diversity and broader coverage of the task space.