NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#process-reward

0 stories this week · 2 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relateddata-science-agents1 deepseek1 dspredict1 grpo1 knowgpo1 qwen1 reinforcement-learning1 search-agents1

2 stories, newest first · one card per story

Hugging Face daily papers20d ago

AdaPRA adds adaptive process rubrics for data science agents

Five attempts per task raised an 80B Qwen model’s leaderboard percentile by 24.5 on DSPredict-Easy and 14.8 on DSPredict-Hard.

process-reward data-science-agents

1

arXiv cs.AI / cs.LG / cs.CL27d ago

KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents

KnowGPO credits search-agent steps by knowledge gained, lifting an 8B model 3.8–4.2 points over process-RL baselines.

knowgpo reinforcement-learning

2