reinforcement learning · 21 topics

microsoft orchard framework

echoverse deep evolving environments for computer use agents

goodfire silico fixes ai training collapse

controlling reasoning effort in llms

the little book of reinforcement learning

nvidia vera rubin maximizes intelligence per dollar

incentivizing temporal awareness in egocentric video understanding models

nvidia research advances robotics from simulation to the real world

2026 05 23 papers 2605.20189 solar lifelong learning

where the goblins came from

recursive synthetic terminal tasks

abseeker long horizon search agents

svr self verifying refinement

cort counterfactual replay for token level rubric guided policy optimization

craft learn the schema execute the plan

arex recursively self improving agent deep research

openforgerl harness native agents

mirror learning from the other view for multi modal reasoning

toolanchor anchoring counterfactual context

mt editflow

qwen agentworld