SOURCE-LINKED INTELLIGENCE

Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Self-evolving reasoning frameworks train a Challenger to generate questions exposing a Solver's weaknesses, creating adaptive curricula without human data. However, existing approaches use a single solver's sampling uncertainty as the Challenger's reward. This creates a fundamental bottleneck: as the solver grows confident on the Challenger's question distribution, all sampled answers converge identically, collapsing the reward to zero and starving the Challenger of learning signal. Critically, this single-model reward cannot distinguish genuinely easy questions from those that merely align wi

Read original source ↗ Open in workspace

recordType

paper

region

Global