Reasoning & Test-Time Compute · 2024
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Establishes 'compute-optimal' test-time scaling, allocating inference compute by problem difficulty so a small model can beat a 14x-larger one, framing the test-time-compute axis.
Editorial record
Plain-language summary
Establishes 'compute-optimal' test-time scaling, allocating inference compute by problem difficulty so a small model can beat a 14x-larger one, framing the test-time-compute axis.
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-631
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2408.03314
- arXiv:2408.03314
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.