From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Paper • 2607.23802 • Published • 99
AI & ML interests
None defined yet.
Recent Activity
View all activity
Benjamin-eecs
authored a
paper 4 days ago
simonycl
updated a
dataset 21 days ago
simonycl
published a
dataset 21 days ago
simonycl
updated 17
models 25 days ago
spiral-rl/qwen3-8b-0708-games-bothink-iter207
8B • Updated • 19
spiral-rl/qwen3-8b-0708-games-bothink-iter175
8B • Updated • 20
spiral-rl/qwen3-8b-0708-games-bothink-iter191
8B • Updated • 19
spiral-rl/qwen3-8b-0708-games-bothink-iter239
8B • Updated • 20
spiral-rl/qwen3-8b-0708-games-bothink-iter223
8B • Updated • 20
spiral-rl/qwen3-8b-0708-games-bothink-iter255
8B • Updated • 16
spiral-rl/qwen3-8b-0708-games-bothink-iter271
8B • Updated • 23
spiral-rl/qwen3-8b-0708-games-bothink-iter287
8B • Updated • 19
spiral-rl/qwen3-8b-0708-games-bothink-iter399
8B • Updated • 16
spiral-rl/qwen3-8b-0708-games-bothink-iter351
8B • Updated • 16
spiral-rl/qwen3-8b-0708-games-bothink-iter111
8B • Updated • 20
spiral-rl/qwen3-8b-0708-games-bothink-iter367
8B • Updated • 13
spiral-rl/qwen3-8b-0708-games-bothink-iter47
8B • Updated • 16
spiral-rl/qwen3-8b-0708-games-bothink-iter95
8B • Updated • 19
spiral-rl/qwen3-8b-0708-games-bothink-iter383
8B • Updated • 13
spiral-rl/qwen3-8b-0708-games-bothink-iter63
8B • Updated • 20
spiral-rl/qwen3-8b-0708-games-bothink-iter79
8B • Updated • 16