RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
Saturn: Sat-based reinforcement learning to unleash llms reasoning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
SCALER creates adaptive synthetic environments for RL-based LLM reasoning training that outperforms fixed-dataset baselines with more stable long-term progress.
EvoCoT uses self-generated and verified CoT trajectories in a two-stage curriculum to let LLMs learn from initially unsolved hard problems in RLVR settings.
citing papers explorer
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
-
SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning
SCALER creates adaptive synthetic environments for RL-based LLM reasoning training that outperforms fixed-dataset baselines with more stable long-term progress.
-
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning
EvoCoT uses self-generated and verified CoT trajectories in a two-stage curriculum to let LLMs learn from initially unsolved hard problems in RLVR settings.