WeaveAgent：面向超高分辨率遥感影像的两阶段工具路由智能体
WeaveAgent: A Two-Stage Tool-Routing Agent for Ultra-High-Resolution Remote Sensing Imagery
- National University of Defense Technology（国防科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
WeaveAgent提出两阶段工具路由方法，将路由与视觉感知解耦，通过SFT和GRPO训练，显著提升外在路由准确率，并揭示了观察加载和两轮SFT对答案准确率的贡献。
AI中文摘要：
问题。具有模糊用户意图的超高分辨率（UHR）遥感存在两个瓶颈：视觉标记成本高昂，且工具调用必须格式可靠（预训练模型零样本时不会发出任何工具调用）。方法。WeaveAgent，一个两阶段工具路由智能体，将路由与视觉感知解耦。阶段A以路由优先：发射是经过训练的，而非诱发的。阶段B有条件地执行：内在查询进入视觉回答（全场景缩略图；一个WeaveEarth风格的证据板作为可选固定预算、约5k标记的压缩接口）；外在查询在原始全分辨率影像上执行工具调用，并在第二轮观察掩蔽轮次中根据工具观察结果进行回答。训练：对齐SFT，然后在奖励R_WA2下进行GRPO。结果。对齐SFT将外在路由从0%提升至80.75%（323/400）；GRPO抑制了9次内在误发射，而工具选择保持不变。训练后的2B系统整体上未超越零样本8B基线（0.263对0.250），这是一个诊断性贡献。Oracle归因分离了两种修复成分：将观察加载到上下文中，在无标记跨模态返回下将外在答案准确率从0.025提升至0.425，而两轮SFT阶段进一步增加+9.3个百分点至0.518，代价是较小的路由成本。+/-图像消融显示发射抑制具有视觉基础，查询注册矩阵显示LLM重写的查询使训练后的检查点损失2-11个百分点。范围。所有训练和评估均使用5,000/3,273/1,000条记录的VagueUHR语料库（600条内在+400条需要工具；基础种子用于合成，不用于优化）。单遍证据构建在RTX 4090上每张图像运行7.31秒。代码、数据和评估协议将发布。
英文摘要：
Problem. Ultra-high-resolution (UHR) remote sensing with vague user intents has two bottlenecks: visual tokens are expensive, and tool calling must be format-reliable (pretrained models emit zero tool calls zero-shot). Method. WeaveAgent, a two-stage tool-routing agent, decouples routing from visual perception. Stage A is routing-first: emission is trained, not elicited. Stage B executes conditionally: intrinsic queries enter visual answering (full-scene thumbnail; a WeaveEarth-style evidence board as an optional fixed-budget, approx. 5k-token compression interface); extrinsic queries execute tool call on original full-resolution imagery, answering from tool observations in a second, observation-masked round. Training: alignment SFT, then GRPO under reward R_WA2. Results. Alignment SFT lifts extrinsic routing from 0% to 80.75% (323/400); GRPO suppresses 9 intrinsic mis-emissions while tool selection is unchanged. The trained 2B system does not beat the zero-shot 8B baseline overall (0.263 vs. 0.250), a diagnostic contribution. Oracle attribution separates two repair ingredients: loading the observation into context lifts extrinsic answer accuracy from 0.025 to 0.425 under marker-free cross-mode returns, and the two-turn SFT stage adds a further +9.3 points to 0.518 at a small routing cost. A +/- image ablation shows emission suppression is visually grounded, and a query-register matrix shows LLM-rewritten queries cost trained checkpoints 2-11 points. Scope. All training and evaluation use the 5,000 / 3,273 / 1,000-record VagueUHR corpus (600 intrinsic + 400 tool-requiring; the base seeds synthesis and is not used for optimization). Single-pass evidence construction runs at 7.31 s per image on an RTX 4090. Code, data, and evaluation protocols will be released.
