EvoEnv lets a single policy synthesize, validate, and use Python environments with durable solve-verify asymmetry to improve reasoning performance on Qwen3-4B-Thinking from 72.4 to 74.8 while fixed-data baselines decline.
How far can unsupervised rlvr scale llm training?
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
other 1polarities
unclear 1representative citing papers
Prune-OPD detects prefix drift via top-k overlap and dynamically prunes unreliable teacher rewards in OPD, cutting training time 37.6-68% on AMC/AIME/HMMT while preserving performance.
citing papers explorer
-
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
EvoEnv lets a single policy synthesize, validate, and use Python environments with durable solve-verify asymmetry to improve reasoning performance on Qwen3-4B-Thinking from 72.4 to 74.8 while fixed-data baselines decline.
-
Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
Prune-OPD detects prefix drift via top-k overlap and dynamically prunes unreliable teacher rewards in OPD, cutting training time 37.6-68% on AMC/AIME/HMMT while preserving performance.