Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding

TL;DR

This paper proposes a staged knowledge injection recipe: cold-starting with scalable, knowledge-graph-verified Earth-science text QA to instill reasoning structures, and pre-warming on the same hard UHR image-text examples during SFT to stabilize and amplify subsequent tool-based RL.

Abstract

Multimodal reasoning for ultra-high-resolution (UHR) remote sensing (RS) is usually bottlenecked by visual evidence acquisition: the model necessitates localizing tiny task-relevant regions in massive pixel spaces. While Agentic Reinforcement Learning with Verifiable Rewards (RLVR) using zoom-in tools offers a path forward, we find that standard reinforcement learning struggles to navigate these vast visual spaces without structured domain priors. In this paper, we investigate the interplay between post-training paradigms: comparing Cold-start Supervised Fine-Tuning (SFT), RLVR, and Agentic RLVR on the UHR RS benchmark.Our controlled studies yield a counter-intuitive finding: high-quality Earth-science text-only QA is a primary driver of UHR visual reasoning gains. Despite lacking images, domain-specific text injects the concepts, mechanistic explanations, and decision rules necessary to guide visual evidence retrieval.Based on this, 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. This approach achieves a 60.40% Pass@1 on XLRS-Bench, significantly outperforming larger general purpose models (e.g., GPT-5.2, Gemini 3.0 Pro, Intern-S1) and establishing a new state-of-the-art.

Figures (6)

• Figure 1: We investigate the interplay between post-training paradigms and found that Earth-science text-only QA is a primary driver of UHR visual reasoning gains. Finally, Agentic RLVR, trained on our datasets with our method, significantly outperforms existing MLLMs on UHR RS tasks.
• Figure 2: The impact of domain data on performance across different training methods.
• Figure 3: The impact of cold-start SFT and RL-stage domain knowledge injection on Pass@1 and Pass@32 in Agentic RLVR. We only use the VQA data (SuperRs-VQA) as the Domain Data. The findings of ① ② ③ are detailed in the main text. Cold-start SFT with domain data yields consistent improvements in both average performance (Pass@1) and reasoning boundary (Pass@32), whereas incorporating domain knowledge only during RL produces smaller or less stable gains, highlighting the importance of staged image-text knowledge incorporation.
• Figure 4: Effects of domain knowledge modality and injection stage on Agentic RLVR performance.
• Figure 5: Automated pipeline for Earth-science text QA generation.Panel A shows textbook-based construction that produces candidate exercise-style QA grounded in foundational concepts through corpus collection, cleaning, normalization, and reasoning refinement. Panel B shows paper-based construction that produces candidate literature-style QA targeting frontier topics and complex reasoning through paper parsing, task categorization, and template-guided generation with multi-stage checks. Panel C builds a textbook-derived knowledge graph from the cleaned textbook corpus and uses it to screen and validate candidates from Panels A and B for domain relevance as well as factual and logical consistency.