An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models Paper • 2408.00724 • Published Aug 1, 2024 • 2
Learn Hard Problems During RL with Reference Guided Fine-tuning Paper • 2603.01223 • Published Mar 1 • 13
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution Paper • 2606.01286 • Published 7 days ago • 5
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution Paper • 2606.01286 • Published 7 days ago • 5
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution Paper • 2606.01286 • Published 7 days ago • 5
BenchEvolver/gpt-oss-20b-lcb-all-seeds-run02-step100 Reinforcement Learning • 21B • Updated 5 days ago • 16
BenchEvolver/gpt-oss-20b-lcb-all-seeds-run02-step100 Reinforcement Learning • 21B • Updated 5 days ago • 16
BenchEvolver/gpt-oss-20b-lcb-all-seeds-run01-step100 Reinforcement Learning • 21B • Updated 5 days ago • 13
BenchEvolver/gpt-oss-20b-lcb-all-seeds-run01-step100 Reinforcement Learning • 21B • Updated 5 days ago • 13
BenchEvolver/gpt-oss-20b-lcb-all-evolved-problems-run02-step100 Reinforcement Learning • 21B • Updated 5 days ago • 15
BenchEvolver/gpt-oss-20b-lcb-all-evolved-problems-run02-step100 Reinforcement Learning • 21B • Updated 5 days ago • 15
BenchEvolver/gpt-oss-20b-lcb-all-evolved-problems-run01-step100 Reinforcement Learning • 21B • Updated 5 days ago • 14
BenchEvolver/gpt-oss-20b-lcb-all-evolved-problems-run01-step100 Reinforcement Learning • 21B • Updated 5 days ago • 14
BenchEvolver/gpt-oss-20b-lcb-all-seeds-and-evolved-run01-step100 Reinforcement Learning • 21B • Updated 5 days ago • 14
BenchEvolver/gpt-oss-20b-lcb-all-seeds-and-evolved-run01-step100 Reinforcement Learning • 21B • Updated 5 days ago • 14
BenchEvolver/gpt-oss-20b-lcb-all-seeds-and-evolved-run02-step100 Reinforcement Learning • 21B • Updated 5 days ago • 14
BenchEvolver/gpt-oss-20b-lcb-all-seeds-and-evolved-run02-step100 Reinforcement Learning • 21B • Updated 5 days ago • 14