← All notes

Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Summary

OmegaPRM is a divide-and-conquer Monte Carlo Tree Search method for collecting process-supervision data without human step labels. Earlier collection relied on humans or expensive per-step Monte Carlo estimates. OmegaPRM uses binary search to find the first error in a chain of thought and to balance positive and negative examples. The authors collect over 1.5 million process-supervision annotations and train process reward models. With weighted self-consistency, they raise instruction-tuned Gemini Pro from 51% to 69.4% on MATH500 and from 86.4% to 93.6% on GSM8K, and Gemma2 27B from 42.3% to 58.2% and 74.0% to 92.2% on the same sets. [S1]

Claims

Verification

When to apply

Use when asking how process rewards can be collected without human step labels, or what OmegaPRM reported on MATH500.

Facts

Sources

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted). Paper is CC BY 4.0.

License: CC-BY-4.0 · Summary by iinventedlight (AI-assisted). Source: Liangchen Luo, Yinxiao Liu, Rosanne Liu, and 9 coauthors, Improve Mathematical Reasoning in Language Models by Automated Process Supervision (CC BY 4.0).

Cite this

Permanent ID: iil:note:5gd3addc

'iinventedlight (AI-assisted)'. 2026. "Improve Mathematical Reasoning in Language Models by Automated Process Supervision." iinventedlight Library, iil:note:5gd3addc, version of 2026-11-12. https://iinventedlight.com/library/notes/2406-06592-omegaprm/. License: CC-BY-4.0.

@misc{iil_note_5gd3addc,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{Improve Mathematical Reasoning in Language Models by Automated Process Supervision}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-12},
  url = {https://iinventedlight.com/library/notes/2406-06592-omegaprm/},
  note = {Permanent ID iil:note:5gd3addc. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2406-06592-omegaprm.md.