Reasoning & Test-Time Compute · 2025
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
A single model proposes and solves its own verifiable tasks with no human-curated data, reaching SOTA math and code reasoning and removing the human-question bottleneck in RLVR.
Editorial record
Plain-language summary
A single model proposes and solves its own verifiable tasks with no human-curated data, reaching SOTA math and code reasoning and removing the human-question bottleneck in RLVR.
Knowledge graph
Relationships
Descendants
Conceptual ancestorEvidence: Strongly supported
Chain-of-Thought Prompting Elicits Reasoning
Builds on the reasoning lineage in the archive
freshness sweep 2026
Source record
Provenance
- Record ID
- P-644
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2505.03335
- arXiv:2505.03335
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.