Hard examples are all you need: Maximizing grpo post-training under annotation budgets

representative citing papers

citing papers explorer

Showing 4 of 4 citing papers.

• Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation cs.LG · 2026-07-08 · conditional · none · ref 19

  Left-shifting iterative compiler/test refinement into verified SFT data, then GRPO on difficulty-curated IO rewards, lifts Qwen3-8B Julia pass@1 past prior SOTA at 1/3 data and 1/6 cost, and bootstraps Ballerina.

• Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF cs.LG · 2026-07-08 · conditional · none · ref 29

  Two plug-and-play strategies — per-timestep advantage weighting and advantage-based trajectory replay — improve diffusion RLHF sample efficiency up to 6× across five reward functions.

• Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation cs.LG · 2026-06-07 · unverdicted · none · ref 14

  AdaGRPO gates GRPO reinforcement learning with supervised NLL using per-sample binary clips based on policy difficulty and reward discriminability, raising HR@10 from 11.01% to 12.18% while keeping hallucination below 0.22% on large-scale e-commerce data and showing A/B gains.

• LLM Reasoning with Process Rewards for Outcome-Guided Steps cs.LG · 2026-02-08 · unverdicted · none · ref 25

  PROGRS uses outcome-conditioned centering on PRM scores to safely integrate process rewards into GRPO for improved Pass@1 on math benchmarks.