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.
1 stories, newest first · one card per story
KnowGPO credits search-agent steps by knowledge gained, lifting an 8B model 3.8–4.2 points over process-RL baselines.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views