Skill Self-Play combines task generation, solution search, and dynamic skill control in a reinforcement learning loop to achieve both task diversity and training reliability.
Surrogate Latent Policy Optimization enables efficient outcome-reward training for latent reasoners that use continuous vectors instead of tokens for intermediate steps.
SEED leverages self-generated hindsight supervision from language model-native trajectory analysis to bridge the supervision gap between episode-level outcomes and token-level learning signals.
Direct-OPD transfers RL-induced policy shifts from weaker to stronger models by leveraging the implicit reward signal from the log-ratio of the RL-shifted and original policy.
Reinforcement Learning with Metacognitive Feedback (RLMF) enables LLMs to express their own uncertainty in a calibrated manner and outperforms standard RL methods by up to 63 percent.
Structured curriculum learning strategies that leverage task relationships in latent space achieve better downstream performance than pure difficulty prioritization.
STARE uses surprisal metrics and selective advantage reweighting to maintain policy entropy stability across long training sequences while improving accuracy by 4–8%.
RACES enables automatic composition of verifiable environments through recursive combination, with DeepSeek-R1-Distill-Qwen-14B improving by 3.1 points and Qwen3-14B by 2.3 points across six benchmarks.
FlowTracer models information propagation as a directed graph and derives token credits from global flow structure to precisely concentrate reinforcement learning signals on critical reasoning steps.
