CVMar 10

GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision

arXiv:2603.09551v125.4h-index: 6
Predicted impact top 21% in CV · last 90 daysOriginality Highly original
AI Analysis

This addresses the problem of unreliable reasoning in remote sensing for applications like environmental monitoring, though it is incremental by building on existing chain-of-thought methods.

The paper tackles the challenge of ensuring visual faithfulness in step-by-step reasoning for remote sensing interpretation by introducing GeoSolver, a framework that uses process-supervised reinforcement learning, achieving state-of-the-art performance across diverse benchmarks and enabling robust test-time scaling.

While Vision-Language Models (VLMs) have significantly advanced remote sensing interpretation, enabling them to perform complex, step-by-step reasoning remains highly challenging. Recent efforts to introduce Chain-of-Thought (CoT) reasoning to this domain have shown promise, yet ensuring the visual faithfulness of these intermediate steps remains a critical bottleneck. To address this, we introduce GeoSolver, a novel framework that transitions remote sensing reasoning toward verifiable, process-supervised reinforcement learning. We first construct Geo-PRM-2M, a large-scale, token-level process supervision dataset synthesized via entropy-guided Monte Carlo Tree Search (MCTS) and targeted visual hallucination injection. Building upon this dataset, we train GeoPRM, a token-level process reward model (PRM) that provides granular faithfulness feedback. To effectively leverage these verification signals, we propose Process-Aware Tree-GRPO, a reinforcement learning algorithm that integrates tree-structured exploration with a faithfulness-weighted reward mechanism to precisely assign credit to intermediate steps. Extensive experiments demonstrate that our resulting model, GeoSolver-9B, achieves state-of-the-art performance across diverse remote sensing benchmarks. Crucially, GeoPRM unlocks robust Test-Time Scaling (TTS). Serving as a universal geospatial verifier, it seamlessly scales the performance of GeoSolver-9B and directly enhances general-purpose VLMs, highlighting its remarkable cross-model generalization.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes