cs.AINov 4, 2026

GIST: Gibbs-Targeted Hierarchical Data Selection for Offline RLVR

Authors: Xuliang Huang, Tianxiang Zhao, Chengwei Qin, Yao Shu

Organizations: The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology

Abstract

Offline reinforcement learning with verifiable rewards (RLVR) trains on a fixed pool of sampled responses and typically supervises every token of every response, although responses and tokens are not equally informative. We study which ones to supervise through the Gibbs-optimal policy of KL-regularized RLVR, which offline training targets, and measure the mismatch between a policy and this target with a bidirectional KL divergence. At the reference policy, this mismatch factorizes exactly and separates the two outcomes: correct responses contribute mainly through the forward term, concentrated on their low-probability tokens, and incorrect responses through the reverse term, concentrated on the responses the policy generates often and on their high-probability tokens. Based on this analysis, we propose GIST (Gibbs-Targeted Hierarchical Data Selection), a two-level selection method that approximates these principles with signals available before training. GIST uses the sampling temperature to select correct responses on-policy and incorrect responses near the policy's mode, and it uses the initial policy's token probabilities to supervise only the tokens where the mismatch lies. Applied to two offline training objectives, GIST raises the average accuracy over GSM8K, MATH-500, and MBPP for all three models under both objectives. In a controlled comparison on Qwen3-0.6B/GSM8K, it outperforms seven selection baselines that choose from the same candidates while supervising 66.6% fewer tokens than training on all candidates of the same prompts.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 13, 2026

Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization

Off-policy data in reinforcement learning with verifiable rewards (RLVR) can arise from asynchronous generation, rollout-training mismatch, and response reuse. Token-wise importance weighting avoids multiplying likelihood ratios across a response but generally biases policy gradients. We prove that, under coverage and local expressiveness conditions, full future KL credit makes the exact proximal optimizer the update's unique stationary policy, even for mixtures of older policies, without full-response weights or a fitted critic. We further establish convergence of continuous-time tabular population updates under persistent coverage and time-varying behavior policies, and a finite-sample reward guarantee for linear logistic models under additional assumptions. These results motivate Proximal KL, a practical off-policy RLVR method that separates the proximal reference from the sampling policy and replaces PPO clipping with bounded future KL credit. Across all seven matched off-policy comparisons on Qwen3-1.7B and Qwen3-4B, spanning two learning rates, response reuse, and rollout staleness, Proximal KL outperforms GRPO in micro-averaged accuracy over eight math benchmarks by up to 2.58%. A separate on-policy comparison yields comparable aggregate accuracy. In periodic-refresh experiments, Proximal KL avoids the collapses observed in PG and CISPO, exceeds GRPO's training accuracy, and reaches higher accuracy in fewer policy updates. Ablations show that token-wise correction outperforms sequence-level and unweighted controls. With token-wise correction retained, future KL feedback reduces sensitivity to the tested baseline perturbation relative to PPO clipping. A finite future horizon improves AIME24 mean@16 and pass@16 over the full tail, while fixed-policy measurements show that truncation reduces correction variance over the tested horizons.
Oct 14, 2026

Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards

Reinforcement learning with verifiable rewards often trains language models on responses generated by a different, possibly stale behavior policy. Correcting this mismatch with learner-to-behavior importance weights can introduce high variance for long responses. We introduce Gibbs-Gap Policy Optimization (GGPO), which minimizes a log-mean-exp contrast of KL-adjusted rewards among responses to the same prompt, without learner-to-behavior importance weights. We derive GGPO from KL-regularized policy optimization: on policy, its population loss is exactly the KL-regularized optimality gap, and under suitable coverage the learner's single-response expected reward is at least the behavior policy's best-of-KK reward, minus terms for the raw finite-group loss, regularization, and finite training data. We characterize reference refresh through exact Gibbs-target composition and a finite-data final-policy reward bound under local reference control and tokenwise behavior mismatch. This refresh is empirically important: in an ablation, fixed-reference GGPO scores 32.9632.96 on the five-benchmark problem-weighted average, versus 46.5846.58 with the default refresh schedule. Experiments on mathematical reasoning further show that GGPO outperforms GRPO and AGRO under training-inference mismatch and on fixed offline data, while maintaining its performance as controlled policy staleness grows.
Sep 28, 2026

MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but incurs substantial costs from rollouts and policy updates. Online prompt selection improves efficiency by using per-prompt Bayesian posteriors to predict difficulty and prioritize informative prompts. However, existing methods overlook how reliably learning signals are extracted from sampled responses. In GRPO, a response's advantage depends on both its own outcome and the randomly sampled outcomes of its peers through group normalization. Our theoretical and experimental analyses show that uncertainty in group composition introduces composition noise, a non-vanishing variance component that imposes an irreducible lower bound on gradient estimation error and impairs downstream prompt selection. We propose MaPP (Marginalized Posterior-Predictive), a unified framework for data-efficient RLVR that denoises response-level advantage estimation and improves prompt selection using a shared Beta posterior. For each response, MaPP replaces the standard group-relative advantage with a composition-invariant intrinsic advantage through closed-form Beta-Binomial marginalization. The resulting posterior-predictive estimator has an error that provably diminishes as the posterior concentrates. Using the same posterior, MaPP derives an uncertainty-aware prompt selection score to improve data efficiency without additional rollout cost. Experiments on mathematics, planning, and visual geometry across five model backbones show that MaPP consistently outperforms GRPO and strong selection baselines, achieving up to +2.45 average accuracy improvement over the strongest baseline under the same rollout budget and setting a new state of the art.