Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

• URL: http://arxiv.org/abs/2509.21882v1
• Date: Fri, 26 Sep 2025 05:06:25 GMT
• Title: Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
• Authors: Aaron Tu, Weihao Xuan, Heli Qi, Xu Huang, Qingcheng Zeng, Shayan Talaei, Yijia Xiao, Peng Xia, Xiangru Tang, Yuchen Zhuang, Bing Hu, Hanqun Cao, Wenqi Shi, Tianang Leng, Rui Yang, Yingjian Chen, Ziqi Wang, Irene Li, Nan Liu, Huaxiu Yao, Li Erran Li, Ge Liu, Amin Saberi, Naoto Yokoya, Jure Leskovec, Yejin Choi, Fang Wu,
• Abstract summary: We argue that gains are often overstated due to three forces - an RLVR tax, evaluation pitfalls, and data contamination.<n>We propose a tax-aware training and evaluation protocol that co-optimizes accuracy, grounding, and calibrated abstention.
• Score: 110.47944672736723
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning with verifiable rewards (RLVR) is a practical and scalable approach to enhancing large language models in areas such as math, code, and other structured tasks. Two questions motivate this paper: how much of the reported gains survive under strictly parity-controlled evaluation, and whether RLVR is cost-free or exacts a measurable tax. We argue that progress is real, but gains are often overstated due to three forces - an RLVR tax, evaluation pitfalls, and data contamination. Using a partial-prompt contamination audit and matched-budget reproductions across base and RL models, we show that several headline gaps shrink or vanish under clean, parity-controlled evaluation. We then propose a tax-aware training and evaluation protocol that co-optimizes accuracy, grounding, and calibrated abstention and standardizes budgeting and provenance checks. Applied to recent RLVR setups, this protocol yields more reliable estimates of reasoning gains and, in several cases, revises prior conclusions. Our position is constructive: RLVR is valuable and industry-ready; we advocate keeping its practical benefits while prioritizing reliability, safety, and measurement.

Related papers

• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation [52.62655622099456]
  We propose reinforcement learning with verifiable reference-based rewards (RLVRR)<n>Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e., reward chain)<n>In this way, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts, and style, which evaluates adherence to stylistic properties.
  arXiv  Detail & Related papers  (2026-01-26T14:39:58Z)
• Aletheia: What Makes RLVR For Code Verifiers Tick? [51.371034079170435]
  Verifiers trained via Reinforcement Learning from Verifiable Rewards (RLVR) are a prominent fixture of the Large Language Model (LLM) post-training pipeline.<n>Code verifiers remain valuable toward judging model outputs in scenarios where execution feedback is hard to obtain.<n>We examine components of the RLVR-based verifier training recipe widely credited for its success.
  arXiv  Detail & Related papers  (2026-01-17T22:30:45Z)
• OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification [91.15649744496834]
  We propose the Outcome-based Process Verifier (OPV), which verifies the rationale process of summarized outcomes from long chains of thought.<n>OPV achieves new state-of-the-art results on our held-out OPV-Bench, outperforming much larger open-source models such as Qwen3-Max-Preview with an F1 score of 83.1 compared to 76.3.
  arXiv  Detail & Related papers  (2025-12-11T15:47:38Z)
• Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning [3.437656066916039]
  Reinforcement with Verifiable Rewards (RLVR) has emerged as a promising approach for enhancing such capabilities.<n>We investigate RLVR on two problems with fully verifiable solutions.<n>We find that RLVR improves evaluation metrics but often by reinforcing superficial Learning metrics rather than acquiring new reasoning strategies.
  arXiv  Detail & Related papers  (2025-10-30T23:16:02Z)
• Local Coherence or Global Validity? Investigating RLVR Traces in Math Domains [13.626335241662977]
  Reinforcement Learning with Verifiable Rewards (RLVR)-based post-training of Large Language Models (LLMs) has been shown to improve accuracy on reasoning tasks.<n>We investigate the effect of RL post-training on intermediate tokens which are not directly incentivized.
  arXiv  Detail & Related papers  (2025-10-20T23:58:31Z)
• SPARK: Synergistic Policy And Reward Co-Evolving Framework [84.22494672256894]
  We introduce the Synergistic Policy And Reward Co-Evolving Framework (SPARK), an efficient, on-policy, and stable method that builds on RLVR.<n>Instead of discarding rollouts and correctness data, SPARK recycles this valuable information to simultaneously train the model itself as a generative reward model.<n>We show that SPARK achieves significant performance gains on multiple LLM and LVLM models and multiple reasoning, reward models, and general benchmarks.
  arXiv  Detail & Related papers  (2025-09-26T17:50:12Z)
• ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs [32.13266235550995]
  Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs)<n>Inspired by observations from human learning, we introduce a RL technique that integrates verifiable outcomes with the model's own confidence estimates.
  arXiv  Detail & Related papers  (2025-09-22T13:00:35Z)
• CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models [85.315711639214]
  We introduce Curiosity-Driven Exploration (CDE), a framework that leverages the model's own intrinsic sense of curiosity to guide exploration.<n>For the actor, we use perplexity over its generated response, and for the critic, we use the variance of value estimates from a multi-head architecture.<n>Our theoretical analysis shows that the actor-wise bonus inherently penalizes overconfident errors and promotes diversity among correct responses.
  arXiv  Detail & Related papers  (2025-09-11T17:59:17Z)
• Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR [25.56828724912418]
  Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming.<n>Despite its promise, the RLVR paradigm poses significant challenges, as existing methods often suffer from sparse reward signals and unstable policy gradient updates.<n>We propose $textbfPACS$, a novel RLVR framework that achieves im$textbfP$licit $textbfA$ctor $textbfC$ritic coupling.
  arXiv  Detail & Related papers  (2025-09-02T17:22:46Z)
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains [9.917318870162365]
  Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding.<n>Rubrics have recently been used in evaluation benchmarks to capture such judgments, but their potential as reward signals for on-policy post-training remains underexplored.<n>We introduce RaR, an on-policy reinforcement learning method that extends RLVR beyond verifiable domains by using rubric-based feedback.
  arXiv  Detail & Related papers  (2025-07-23T17:57:55Z)
• Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs [32.99709073885827]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for advancing the reasoning capabilities of Large Language Models (LLMs)<n>However, RLVR-tuned models often underperform their base models on the $Pass@K$ metric for solution-finding.<n>We introduce a more precise evaluation metric, $CoT$-$Pass@K$, which mandates that both the reasoning path and the final answer be correct.
  arXiv  Detail & Related papers  (2025-06-17T07:06:56Z)
• Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning [90.23629291067763]
  A promising approach for improving reasoning in large language models is to use process reward models (PRMs) PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward models (ORMs) To improve a base policy by running search against a PRM or using it as dense rewards for reinforcement learning (RL), we ask: "How should we design process rewards?" We theoretically characterize the set of good provers and our results show that optimizing process rewards from such provers improves exploration during test-time search and online RL.
  arXiv  Detail & Related papers  (2024-10-10T17:31:23Z)
• Strategically Conservative Q-Learning [89.17906766703763]
  offline reinforcement learning (RL) is a compelling paradigm to extend RL's practical utility. The major difficulty in offline RL is mitigating the impact of approximation errors when encountering out-of-distribution (OOD) actions. We propose a novel framework called Strategically Conservative Q-Learning (SCQ) that distinguishes between OOD data that is easy and hard to estimate.
  arXiv  Detail & Related papers  (2024-06-06T22:09:46Z)
• Entire Space Counterfactual Learning: Tuning, Analytical Properties and Industrial Applications [5.9460659646670875]
  Post-click conversion rate (CVR) estimation has long been plagued by sample selection bias and data sparsity issues. This paper proposes a principled method named entire space counterfactual multi-task model (ESCM$2$), which employs a counterfactual risk minimizer to handle both IEB and PIP issues at once.
  arXiv  Detail & Related papers  (2022-10-20T06:19:50Z)
• Continuous Doubly Constrained Batch Reinforcement Learning [93.23842221189658]
  We propose an algorithm for batch RL, where effective policies are learned using only a fixed offline dataset instead of online interactions with the environment. The limited data in batch RL produces inherent uncertainty in value estimates of states/actions that were insufficiently represented in the training data. We propose to mitigate this issue via two straightforward penalties: a policy-constraint to reduce this divergence and a value-constraint that discourages overly optimistic estimates.
  arXiv  Detail & Related papers  (2021-02-18T08:54:14Z)

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.