Improve Mathematical Reasoning in Language Models by Automated Process Supervision · HackerPapers discussions

Improve Mathematical Reasoning in Language Models by Automated Process Supervision — mentioned by AlexCoventry

Fri, 28 Nov 2025 03:51:56 GMT

"Process-oriented" verification has been a thing for a while in mathematical reasoning CoT. Google had a paper about it last year [1]. The key term to look for is "Process-reward model." I particularly like RL Tango [2]. [1] https://arxiv.org/abs/2406.06592 [2] https://arxiv.org/abs/2505.15034

Paper and discussion history. A mention is not an endorsement.

Improve Mathematical Reasoning in Language Models by Automated Process Supervision — HN submission

Thu, 04 Jul 2024 17:54:35 GMT

Improve Mathematical Logic in Language Models by Automated Process Supervision

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Improve Mathematical Reasoning in Language Models by Automated Process Supervision — HN submission

Wed, 12 Jun 2024 15:24:05 GMT

Improve Math Reasoning in Language Models by Automated Process Supervision

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.