41554 blogs · 4,450,554 posts Claim your blog

Record · corpus.blog/posts/01a08c56-b9e4-730a-b8f3-5fe3a9da2880

How to Train an LLM to do proofs: Beyond Verifiable Rewards

tobysimonds.com · published 28 September 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at tobysimonds.com Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 6
Words captured: 2,168

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://matharena.ai/

matharena.ai

https://arxiv.org/abs/2507.15855

arxiv.org

https://github.com/Tufalabs/LLMProofs/blob/main/train/scripts/proofs_7b_grpo.sh

github.com

https://wandb.ai/toby-simonds-tufa-labs/llmjudge_proofs/reports/Proof-WandB--VmlldzoxNDUyMzc3Mw?accessToken=b4evm46718n8ru3ac7pa4btj6n1g369bhvsuxrfn73mo1p3fmu4flsoduhnwl6dl

wandb.ai

https://proceedings.mlr.press/v202/gao23h/gao23h.pdf

proceedings.mlr.press

https://github.com/Tufalabs/LLMProofs

github.com