Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression

2026-09-23

AI Summary

本文针对长时序代理压缩效率问题，提出了一种基于任务证据保护的几何引导记忆压缩方法(GEM)，有效减少了令牌使用量并保持了任务奖励。

Abstract

Long horizon agents accumulate growing interaction histories that increase context and inference costs. We find that geometric redundancy alone is an insufficient criterion for safe compression. Although agent histories exhibit strong low dimensional structure, similar global geometry can preserve very different amounts of task evidence. At identical retained block counts, evidence aware selection raises next action Top 3 retention from 0.31 to 0.69, while centroid similarity remains 0.98. Controlled replacement further shows that action related information can be substantially altered while global geometric measures remain nearly unchanged. Motivated by this gap between geometry and evidence, we introduce Geometry Guided Evidence Preserving Memory (GEM), a training free compressor that protects task and execution evidence before using geometric residuals to complete coverage. GEM reduces mean combined token usage from 2.69M to 2.11M per task, a 21.4% reduction, while maintaining comparable task reward. Our results show that efficient agent history compression should optimize for preserved task evidence rather than geometric coverage alone.

Problem

• long horizon agents
• interaction histories
• geometric redundancy
• task evidence
• compression

Innovation

• Geometry Guided Evidence Preserving Memory
• task evidence preservation
• long-horizon agent compression