Improving Generalization Robustness of Multimodal RLVR

• URL: http://arxiv.org/abs/2608.08802v2
• Date: Fri, 14 Aug 2026 16:52:27 GMT
• Title: Improving Generalization Robustness of Multimodal RLVR
• Abstract summary: Reinforcement Learning with Verifiable Rewards makes large language models more accurate, but the gains are brittle.<n>We propose Prompt-Invariant RLVR (PIRL), consisting of a dynamic trinary reward and a consistency regularizer.<n>Under stress testing, PIRL's average accuracy on benchmarks drops by only $le 1%$, where GRPO drops 3%.
• Score: 44.35945134924193
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA. We trace this to two issues of the standard RL objective. First, the binary verifier conflates format with content, so the reward signal cannot tell a wrong answer apart from a misformatted one. Second, the training distribution covers only a thin slice of the real-world prompts that the model might meet at deployment, so policies that perform well on the training distribution can behave differently under unseen prompts during test. Both failures call for a robust post-training method that helps the policy cover a broader distribution of semantically equivalent prompts, and we identify two measures that help achieve this objective: separating format from semantics in the reward, and applying policy invariance across perturbed prompts with equivalent semantics. We therefore propose Prompt-Invariant RLVR (PIRL), consisting of a dynamic trinary reward and a consistency regularizer based on an embedding-space adversary. Under stress testing, PIRL's average accuracy on benchmarks drops by only $\le 1\%$, where GRPO drops ~3%. On dynamic evaluation, PIRL also achieves the smallest performance drop.

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)
• When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion [0.0]
  Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling.<n>We study this pass@k inversion: after training, the policy may solve fewer distinct problems than its base model at large $k$.<n>The failure concentrates on boundary prompts, where the base model contains rare correct trajectories that are recoverable by sampling but too sparse to reliably appear in finite RLVR rollout groups.
  arXiv  Detail & Related papers  (2026-07-12T17:17:18Z)
• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• sGPO: Trading Inference FLOPs for Training Efficiency in RLVR [15.69155608127456]
  Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query.<n>This leads to two symmetric failure modes: easy queries produce near-zero advantage because the policy already solves them, while unsolvable queries produce no signal because the policy never solves them.<n>We introduce sorted Group Policy Optimization (sGPO), a compute-efficient strategy that trades a small budget of inference FLOPs for a large reduction in wasted training FLOPs.
  arXiv  Detail & Related papers  (2026-06-07T21:47:31Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• R$^2$PO: Decoupling Training Trajectories from Inference Responses for LLM Reasoning [38.722039062040096]
  R$2$PO introduces a lightweight Residual Rollout-Head atop the policy to decouple training trajectories from inference responses.<n>Our method consistently outperforms baselines, achieving average accuracy gains of 3.4% on MATH-500 and 1.3% on APPS.
  arXiv  Detail & Related papers  (2026-01-17T08:30:50Z)
• Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening [36.81125165911328]
  Reinforcement learning is emerging as a primary driver for improving language model reasoning capabilities.<n>We investigate whether current reinforcement learning algorithms merely sharpen the base model's distribution around problems it can already solve.<n>We show that unlikeliness reward mitigates rank bias and improves pass@$N$ across a large range of $N$ in both synthetic and real theorem proving settings.
  arXiv  Detail & Related papers  (2025-06-03T01:15:15Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• Self-regulating Prompts: Foundational Model Adaptation without Forgetting [112.66832145320434]
  We introduce a self-regularization framework for prompting called PromptSRC. PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations.
  arXiv  Detail & Related papers  (2023-07-13T17:59:35Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)

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.