H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning

• URL: http://arxiv.org/abs/2606.29915v1
• Date: Mon, 29 Jun 2026 07:51:25 GMT
• Title: H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning
• Abstract summary: Vision-Language Models (VLMs) often achieve high performance on benchmarks while remaining "black boxes"<n>We propose a framework designed to enhance both performance and interpretability through De-compositional Evidence Grounding.
• Score: 14.276463740862825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) often achieve high performance on benchmarks while remaining "black boxes", yet they remain prone to hallucination or rely on superficial shortcuts. In this work, we propose a framework designed to enhance both performance and interpretability through De-compositional Evidence Grounding. Unlike monolithic inference approaches, our approach forces the model to decompose a global query into a sequence of atomic sub-questions, each requiring an explicit sub-answer and critically a localized evidence bounding box. By grounding intermediate logical steps (e.g. identifying a container, analyzing liquid properties, and assessing environmental context) in specific visual regions, we construct a structured reasoning path that mirrors human-like deduction. This allows the final answer to emerge as a logical consequence of verified visual facts rather than a statistical guess.

Related papers

• Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes [37.743333035442426]
  This paper introduces AD2-Bench, which decomposes reasoning into a structured Chain of Evidence (CoE)<n>Building on this perspective, the authors identify two primary causes of reasoning failure: Spatial Ambiguity and Semantic Uncertainty.<n>They then propose Evidence-grounded Visual Reasoning (EGVOR), which replaces implicit reasoning with the explicit generation of Evidence Atoms.
  arXiv  Detail & Related papers  (2026-08-11T14:23:07Z)
• Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs [6.111899371682025]
  Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT.<n>We propose emph"Decompose, Look, and Reason" (DLR), a reinforced latent reasoning framework.<n>Experiments on vision-centric benchmarks show that DLR consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-04-08T18:52:27Z)
• Seeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understanding [30.498502211349386]
  We present the Knowledge-Augmented Fine-Grained Reasoning Agent (KFRA)<n>KFRA operates through a three-stage closed reasoning loop that emulates expert analysis.<n>It first performs open-vocabulary detection and web-scale retrieval to generate category hypotheses.<n>It then conducts discriminative regions localisation by aligning textual knowledge with visual evidence.
  arXiv  Detail & Related papers  (2026-03-04T06:18:45Z)
• Multimodal Latent Reasoning via Hierarchical Visual Cues Injection [16.779425236020433]
  This work posits that robust reasoning should evolve within a latent space, integrating multimodal signals seamlessly.<n>We propose a novel framework that instills deliberate, "slow thinking" without depending on superficial textual rationales.<n>We show that test-time scaling is effective when incorporating vision knowledge, and that integrating hierarchical information significantly enhances the model's understanding of complex scenes.
  arXiv  Detail & Related papers  (2026-02-05T06:31:12Z)
• RegionReasoner: Region-Grounded Multi-Round Visual Reasoning [69.75509909581133]
  RegionReasoner is a reinforcement learning framework for visual reasoning.<n>It enforces grounded reasoning by requiring each reasoning trace to explicitly cite the corresponding reference bounding boxes.<n>RegionReasoner is optimized with structured rewards combining grounding fidelity and global-local semantic alignment.
  arXiv  Detail & Related papers  (2026-02-03T16:52:16Z)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)
• A Survey on Latent Reasoning [100.54120559169735]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities.<n>CoT reasoning that verbalizes intermediate steps limits the model's expressive bandwidth.<n>Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state.
  arXiv  Detail & Related papers  (2025-07-08T17:29:07Z)
• CLATTER: Comprehensive Entailment Reasoning for Hallucination Detection [60.98964268961243]
  We propose that guiding models to perform a systematic and comprehensive reasoning process allows models to execute much finer-grained and accurate entailment decisions.<n>We define a 3-step reasoning process, consisting of (i) claim decomposition, (ii) sub-claim attribution and entailment classification, and (iii) aggregated classification, showing that such guided reasoning indeed yields improved hallucination detection.
  arXiv  Detail & Related papers  (2025-06-05T17:02:52Z)
• How do Transformers Learn Implicit Reasoning? [67.02072851088637]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning [96.01617809845396]
  Ground-R1 is a reinforcement learning framework that enables grounded visual reasoning without requiring explicit evidence or rationale annotations.<n>Ground-R1 achieves superior performance and exhibits emergent cognitive behaviors such as uncertainty awareness, spatial perception, and iterative refinement.
  arXiv  Detail & Related papers  (2025-05-26T17:51:47Z)

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.