RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understanding

• URL: http://arxiv.org/abs/2604.17504v1
• Date: Sun, 19 Apr 2026 15:50:33 GMT
• Title: RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understanding
• Abstract summary: We propose RS-HyRe-R1, a hybrid reward framework for remote sensing understanding.<n> Experiments show RS-HyRe-R1 effectively mitigates "perceptual inertia", encouraging deeper, more diverse reasoning.
• Score: 22.712555479018203
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) post-training substantially improves remote sensing vision-language models (RS-VLMs). However, when handling complex remote sensing imagery (RSI) requiring exhaustive visual scanning, models tend to rely on localized salient cues for rapid inference. We term this RL-induced bias "perceptual inertia". Driven by reward maximization, models favor quick outcome fitting, leading to two limitations: cognitively, overreliance on specific features impedes complete evidence construction; operationally, models struggle to flexibly shift visual focus across tasks. To address this bias and encourage comprehensive visual evidence mining, we propose RS-HyRe-R1, a hybrid reward framework for RSI understanding. It introduces: (1) a spatial reasoning activation reward that enforces structured visual reasoning; (2) a perception correctness reward that provides adaptive quality anchors across RS tasks, ensuring accurate geometric and semantic alignment; and (3) a visual-semantic path evolution reward that penalizes repetitive reasoning and promotes exploration of complementary cues to build richer evidence chains. Experiments show RS-HyRe-R1 effectively mitigates "perceptual inertia", encouraging deeper, more diverse reasoning. With only 3B parameters, it achieves state-of-the-art performance on REC, OVD, and VQA tasks, outperforming models up to 7B parameters. It also demonstrates strong zero-shot generalization, surpassing the second-best model by 3.16%, 3.97%, and 2.72% on VQA, OVD, and REC, respectively. Code and datasets are available at https://github.com/geox-lab/RS-HyRe-R1.

Related papers

• AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing [37.98676093459165]
  AgenticRag-R1, a reinforcement learning framework, integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space.<n>Experiments show that AgenticRag-R1 consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-08-30T07:31:19Z)
• Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding [78.26501371437013]
  Multimodal reasoning for ultra-high-resolution (UHR) remote sensing (RS) is usually bottlenecked by visual evidence acquisition.<n>We find that standard reinforcement learning struggles to navigate these vast visual spaces without structured domain priors.<n>We propose a staged knowledge injection recipe: (1) cold-starting with scalable, knowledge-graph-verified Earth-science text QA to instill reasoning structures; and (2) "pre-warming" on the same hard UHR image-text examples during SFT to stabilize and amplify subsequent tool-based RL.
  arXiv  Detail & Related papers  (2026-02-15T16:40:33Z)
• 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)
• Asking like Socrates: Socrates helps VLMs understand remote sensing images [21.00494676428488]
  We propose RS-EoT (Remote Sensing Evidence-of-Thought), a language-driven, iterative visual evidence-seeking paradigm.<n>SocraticAgent is a self-play multi-agent system that synthesizes reasoning traces via alternating cycles of reasoning and visual inspection.<n>Experiments show RS-EoT achieves state-of-the-art performance on multiple RS VQA and grounding benchmarks.
  arXiv  Detail & Related papers  (2025-11-27T12:19:37Z)
• 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)
• From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs [13.410543801811992]
  This paper analyzes existing RAG reasoning models and identifies three main failure patterns.<n>We propose TIRESRAG-R1, a novel framework using a think-retrieve-reflect process and a multi-dimensional reward system.<n>Experiments on four multi-hop QA datasets show that TIRESRAG-R1 outperforms prior RAG methods and generalizes well to single-hop tasks.
  arXiv  Detail & Related papers  (2025-07-30T14:29:44Z)
• GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning.<n>Using SEED-Bench-R1, we find that standard GRPO, while improving answer accuracy, often reduces logical coherence between reasoning steps and answers, with only a 57.9% consistency rate.<n>We propose GRPO-CARE, a consistency-aware RL framework optimizing both answer correctness and reasoning coherence without explicit supervision.
  arXiv  Detail & Related papers  (2025-06-19T08:49:13Z)
• Transparent and Robust RAG: Adaptive-Reward Reinforcement Learning for Decision Traceability [15.949084214401692]
  Adaptive-Rewarded Evidence Navigation Agent (ARENA) is a transparent and robust RAG generator framework trained via RL with designed rewards.<n>Based on our structured protocol, KL divergence stabilization, and adaptive reward calculation modules, ARENA enables the RAG generator to identify key evidence, perform structured reasoning, and generate answers with interpretable decision traces.
  arXiv  Detail & Related papers  (2025-05-19T15:40:29Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training [62.536191233049614]
  Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs)<n>This work investigates this problem through extensive experiments on complex card games, such as 24 points, and embodied tasks from ALFWorld.<n>We find that when rewards are based solely on action outcomes, RL fails to incentivize CoT reasoning in VLMs, instead leading to a phenomenon we termed thought collapse.
  arXiv  Detail & Related papers  (2025-03-11T15:17:02Z)

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.