AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

• URL: http://arxiv.org/abs/2605.12495v1
• Date: Tue, 12 May 2026 17:59:47 GMT
• Title: AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
• Abstract summary: We propose AlphaGRPO to enhance multimodal generation capabilities without an additional cold-start stage.<n>Our approach unlocks the model's intrinsic potential to perform advanced reasoning tasks.<n>To address the challenge of providing stable supervision for real-world multimodal generation, we introduce the Decompositional Verifiable Reward (DVReward)
• Score: 52.7128440950672
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without an additional cold-start stage. Our approach unlocks the model's intrinsic potential to perform advanced reasoning tasks: Reasoning Text-to-Image Generation, where the model actively infers implicit user intents, and Self-Reflective Refinement, where it autonomously diagnoses and corrects misalignments in generated outputs. To address the challenge of providing stable supervision for real-world multimodal generation, we introduce the Decompositional Verifiable Reward (DVReward). Unlike holistic scalar rewards, DVReward utilizes an LLM to decompose complex user requests into atomic, verifiable semantic and quality questions, which are then evaluated by a general MLLM to provide reliable and interpretable feedback. Extensive experiments demonstrate that AlphaGRPO yields robust improvements across multimodal generation benchmarks, including GenEval, TIIF-Bench, DPG-Bench and WISE, while also achieving significant gains in editing tasks on GEdit without training on editing tasks. These results validate that our self-reflective reinforcement approach effectively leverages inherent understanding to guide high-fidelity generation. Project page: https://huangrh99.github.io/AlphaGRPO/

Related papers

• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents [23.69429098915734]
  Verifier-Guided Action Selection (VegAS) is a test-time framework designed to improve robustness of MLLM-based embodied agents.<n>We show that VeGAS consistently improves generalization, achieving up to a 36% relative performance gain over strong CoT baselines.
  arXiv  Detail & Related papers  (2026-05-12T18:08:24Z)
• ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback [0.0]
  We propose ReVEL: Multi-Turn Reflective LLM-Heuristic Evolution via Structured Performance Feedback.<n>The core of ReVEL lies in two mechanisms: (i) performance-profile grouping and (ii) multi-turn feedback-driven reflection.<n>Our results highlight multi-turn reasoning with structured grouping as a principled paradigm for automated design.
  arXiv  Detail & Related papers  (2026-03-05T04:52:11Z)
• Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models [23.128973540926552]
  Endogenous Reprompting transforms the model's understanding into an explicit generative reasoning step.<n>We show that SEER consistently outperforms state-of-the-art baselines in evaluation accuracy, reprompting efficiency, and generation quality.
  arXiv  Detail & Related papers  (2026-01-28T06:54:36Z)
• STAR: STacked AutoRegressive Scheme for Unified Multimodal Learning [37.68078190711403]
  We introduce STAR: a STacked AutoRegressive scheme for task-progressive unified multimodal learning.<n>This approach decomposes multimodal learning into multiple stages: understanding, generation, and editing.<n> Experiments demonstrate that STAR achieves state-of-the-art performance on GenEval (0.91), DPG-Bench (87.44), and ImgEdit (4.34)
  arXiv  Detail & Related papers  (2025-12-15T07:02:59Z)
• MURPHY: Multi-Turn GRPO for Self Correcting Code Generation [55.66642560374686]
  Murphy is a multi-turn reflective optimization framework that extends GRPO by incorporating iterative self-correction during training.<n>We show that Murphy consistently improves performance, achieving up to a 8% relative gain in pass@1 over GRPO, on similar compute budgets.
  arXiv  Detail & Related papers  (2025-11-11T05:03:22Z)
• UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings [70.60608084375691]
  We pioneer the exploration of generative embeddings, unifying embedding tasks within a generative paradigm.<n>We propose UME-R1, a universal multimodal embedding framework consisting of a two-stage training strategy.<n> evaluated on the MMEB-V2 benchmark across 78 tasks spanning video, image, and visual documents.
  arXiv  Detail & Related papers  (2025-11-01T05:04:23Z)
• ReVeal: Self-Evolving Code Agents via Reliable Self-Verification [11.875519107421312]
  We introduce ReVeal, a reinforcement learning framework that evolves code generation through self-verification and tool-based evaluation.<n>At inference, this strengthened self-verification enables the model to use self-constructed tests and tool feedback to continuously evolve code for 20+ turns on LiveCodeBench despite training on only three.<n>These findings highlight the promise of ReVeal as a scalable paradigm for RL training and test-time scaling, paving the way for more robust and autonomous AI agents.
  arXiv  Detail & Related papers  (2025-06-13T03:41:04Z)
• SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards [55.99492656542475]
  We propose textbfSUDER (textbfSelf-improving textbfUnified LMMs with textbfDual stextbfElf-textbfRewards), a framework reinforcing the understanding and generation capabilities of LMMs.
  arXiv  Detail & Related papers  (2025-06-09T17:38:45Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution [61.80716438091887]
  GenDiE (Generate, Discriminate, Evolve) is a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimization.<n>By treating each sentence in a response as an independent optimization unit, GenDiE effectively addresses the limitations of previous approaches.<n>Experiments on ASQA (in-domain LFQA) and ConFiQA datasets demonstrate that GenDiE surpasses various baselines in both faithfulness and correctness.
  arXiv  Detail & Related papers  (2025-03-03T16:08:33Z)

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.