Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing

• URL: http://arxiv.org/abs/2602.03452v1
• Date: Tue, 03 Feb 2026 12:17:25 GMT
• Title: Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing
• Abstract summary: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language models on deterministic outcome reasoning tasks.<n>Prior work shows RLVR works with few prompts, but prompt selection is often based only on training-accuracy variance.<n>We argue that an effective minibatch should provide both (i) a reliable positive anchor and (ii) explicit negative learning signals from rare failures.
• Score: 21.946965363578087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language models on deterministic outcome reasoning tasks. Prior work shows RLVR works with few prompts, but prompt selection is often based only on training-accuracy variance, leading to unstable optimization directions and weaker transfer. We revisit prompt selection from a mechanism-level view and argue that an effective minibatch should provide both (i) a reliable positive anchor and (ii) explicit negative learning signals from rare failures. Based on this principle, we propose \emph{positive--negative pairing}: at each update, we sample a hard-but-solvable $q^{+}$ and an easy-but-brittle prompt $q^{-}$(high success rate but not perfect), characterized by low and high empirical success rates under multiple rollouts. We further introduce Weighted GRPO, which reweights binary outcomes at the pair level and uses group-normalized advantages to amplify rare successes on $q^{+}$ into sharp positive guidance while turning rare failures on $q^{-}$ into strong negative penalties. This bidirectional signal provides informative learning feedback for both successes and failures, improving sample efficiency without suppressing exploration. On Qwen2.5-Math-7B, a single paired minibatch per update consistently outperforms a GRPO baseline that selects two prompts via commonly used variance-based selection heuristics: AIME~2025 Pass@8 improves from 16.8 to 22.2, and AMC23 Pass@64 from 94.0 to 97.0, while remaining competitive with large-scale RLVR trained from a pool of 1209 training prompts. Similar gains are observed on Qwen2.5-Math-7B-Instruct.

Related papers

• Verifier-Induced Support Reshaping in On-Policy Optimization [27.782412748608255]
  We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce.<n>We call this verifier-induced support reshaping and define effective rewardable support as successful trajectories reachable within a fixed rollout budget.
  arXiv  Detail & Related papers  (2026-07-31T19:05:43Z)
• ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning [75.26064451955199]
  ExTra is a framework that extracts exploration signals from the model's own rollouts.<n>It improves Qwen3-1.7B over GRPO by about +5 points on pass@1 and +7 points on pass@16.
  arXiv  Detail & Related papers  (2026-06-23T15:51:39Z)
• When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL [10.399451281089318]
  We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test.<n>Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding.<n>We propose diagnostic-driven iterative refinement, where training diagnostics and a failure-mode taxonomy guide targeted reward-function revision.
  arXiv  Detail & Related papers  (2026-05-27T17:57:43Z)
• Leveraging Error Diversity in Group Rollouts for Reinforcement Learning [61.10980882949414]
  Reinforcement Learning from Verifiable Rewards (RLVR) typically samples multiple responses per prompt and assigns binary rewards based on individual correctness.<n>We propose Error Diversity Advantage Shaping (EDAS) to modulate the advantage signal for incorrect rollouts based on intra-group error diversity.<n>EDAS operates as a simple post-hoc adjustment that can be seamlessly integrated into any RLVR algorithm.
  arXiv  Detail & Related papers  (2026-05-17T08:52:31Z)
• Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR [78.88799271719365]
  We introduce arrol (Accelerating RLVR via online Rollout Pruning), an online rollout pruning method.<n>Arrol trains a lightweight quality head on-the-fly to predict the success probability of partial rollouts and uses it to make early pruning decisions.<n>Across GRPO and DAPO on Qwen-3 and LLaMA-3.2 models, arrol improves average accuracy by +2.30 to +2.99 while achieving up to 1.7x training speedup.
  arXiv  Detail & Related papers  (2026-03-25T22:10:36Z)
• Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts [0.0]
  Reinforcement learning with verifiable rewards (RLVR) plays a crucial role in expanding the capacities of reasoning, but GRPO-style training is dominated by expensive rollouts and wastes compute on unusable prompts.<n>We propose Prompt Replay, an overhead-free online data selection method for GRPO that reuses prompts only (not trajectories) to preserve on-policy optimization.
  arXiv  Detail & Related papers  (2026-03-22T11:39:51Z)
• Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards [33.72297722930672]
  We consider asymmetric prompt weightings that assign higher weights to prompts with low, or even zero, empirical success probability.<n>In low-success regimes, where informative responses are rare and response cost dominates, these optimal weights become asymmetric.
  arXiv  Detail & Related papers  (2026-02-11T18:39:42Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models [61.78513830395669]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs)<n>As models train longer and scale larger, more training prompts become residual prompts, those with zero variance rewards that provide no training signal.<n>We propose the Explore Residual Prompts in Policy Optimization framework, which encourages exploration on residual prompts and reactivates their training signals.
  arXiv  Detail & Related papers  (2025-11-06T20:40:27Z)
• Token-Level Inference-Time Alignment for Vision-Language Models [58.41370989069588]
  Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence.<n>We present TITA, a lightweight framework that freezes the base VLM and instead trains a reward model to approximate its distribution.<n>During inference, implicit preference signals are extracted as log-probability ratios between the reward model and the target VLM, yielding dense autoregressive feedback.
  arXiv  Detail & Related papers  (2025-10-20T09:58:03Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping [35.34724727629745]
  We introduce RL with Zero-Variance Prompts (RL-ZVP), a novel algorithm that extract learning signals from zero-variance prompts.<n>RL-ZVP directly rewards correctness and penalizes errors even without contrasting responses.<n>Across six math reasoning benchmarks, RL-ZVP achieves significant improvements of up to 8.61 points in accuracy and 7.77 points in pass rate over GRPO.
  arXiv  Detail & Related papers  (2025-09-26T05:03:54Z)
• The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning [37.13807960501503]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training language models (LMs)<n>We decompose the learning signal into reinforcing correct responses and penalizing incorrect ones, referred to as Positive and Negative Sample Reinforcement (PSR and NSR)<n>We show that NSR works by suppressing incorrect generations and redistributing probability mass toward other plausible candidates, guided by the model's prior beliefs.
  arXiv  Detail & Related papers  (2025-06-02T06:10:54Z)
• WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation [57.11538133231843]
  Keyphrase generation aims to automatically generate short phrases summarizing an input document. The recently emerged ONE2SET paradigm generates keyphrases as a set and has achieved competitive performance. We propose WR-ONE2SET which extends ONE2SET with an adaptive instance-level cost Weighting strategy and a target Re-assignment mechanism.
  arXiv  Detail & Related papers  (2022-11-13T09:56:24Z)
• Supervised Advantage Actor-Critic for Recommender Systems [76.7066594130961]
  We propose negative sampling strategy for training the RL component and combine it with supervised sequential learning. Based on sampled (negative) actions (items), we can calculate the "advantage" of a positive action over the average case. We instantiate SNQN and SA2C with four state-of-the-art sequential recommendation models and conduct experiments on two real-world datasets.
  arXiv  Detail & Related papers  (2021-11-05T12:51:15Z)
• Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling [37.01593605084575]
  TAS-Balanced is an efficient topic-aware query and balanced margin sampling technique. We show that our TAS-Balanced training method achieves state-of-the-art low-latency (64ms per query) results on two TREC Deep Learning Track query sets.
  arXiv  Detail & Related papers  (2021-04-14T16:49:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.