Primary evidence
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningS1 · Primary research · Paper · 2025-01-22
- DeepSeek-R1 model and technical release repositoryS1 · Primary research · Repository
DeepSeek-R1 shows open reinforcement-learned reasoning at frontier math performance
R1-Zero used reinforcement learning without an SFT cold start, while R1 added multi-stage training and released several distilled open models.
What happened?
DeepSeek-R1 and R1-Zero demonstrated strong reasoning behavior from large-scale reinforcement learning, with R1 reported as comparable to OpenAI o1 on reasoning tasks.
Why it matters
The release accelerated open research on reasoning models, verifier-guided RL and math-specific post-training, providing context for later dedicated AI4Math systems.
Significance rationale: DeepSeek-R1 is historically important to general-purpose reasoning-model development, but its relevance to AI4Math is primarily contextual: mathematics served as a capability benchmark rather than the release contributing a mathematical result, proof, formalization, or math-specific system.
Historical context
Earlier developments
Later developments
—
Related milestones
—
Evidence & status at a glance
- Significance
- H3 · Context event
- Verification
- Paper released
- Evidence level
- E3 · Inspectable artifact
- AI role
- Computation only
- Formal assurance
- Artifact available
Contribution & verification
- Mathematical novelty
- Benchmark result
- Interface
- Informal, Symbolic
- AI contribution
- The models perform extended mathematical reasoning learned through reinforcement-learning objectives.
- Human contribution
- Researchers designed the RL and cold-start recipes, trained the models and released weights.
- Verification
- Paper released · E3 · Inspectable artifact · Artifact available
- Last reviewed
- 2026-09-11
Technical details
- Systems
- deepseek-r1
- Organizations
- deepseek
- Problems
- aime, math-benchmark
- Methods
- reinforcement-learning, reasoning-model, distillation
Sources & artifacts
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningS1 · Primary research · Paper · accessed 2026-09-10
- DeepSeek-R1 model and technical release repositoryS1 · Primary research · Repository · accessed 2026-09-11
- DeepSeek-R1 model release and technical artifactsArtifact · Model
Verification history
- 2025-01-22 · Paper released · E2 · Research record
The Chronicle records this event from the cited primary or official source; the status does not imply independent Chronicle verification.
- 2026-09-11 · Paper released · E3 · Inspectable artifact
This corpus refresh added a directly inspectable public artifact maintained by the authors or releasing organization. E3 records artifact-level inspectability and does not imply independent verification of the underlying scientific or mathematical claim.
Corrections
No corrections recorded.