pith. sign in

Knapsack rl: Unlocking exploration of llms via optimizing budget allocation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Selective Off-Policy Reference Tuning with Plan Guidance

cs.AI · 2026-05-12 · unverdicted · novelty 6.0 · 2 refs

SORT turns all-wrong prompts into selective learning signals by weighting tokens more predictable under plan guidance from reference solutions, improving over GRPO on reasoning benchmarks especially for weaker models.

citing papers explorer

Showing 1 of 1 citing paper.

  • Selective Off-Policy Reference Tuning with Plan Guidance cs.AI · 2026-05-12 · unverdicted · none · ref 9 · 2 links

    SORT turns all-wrong prompts into selective learning signals by weighting tokens more predictable under plan guidance from reference solutions, improving over GRPO on reasoning benchmarks especially for weaker models.