SOURCE-LINKED INTELLIGENCE

AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks. However, the trial-and-error nature of these agents generates lengthy interaction trajectories, creating severe bottlenecks in terms of context window limits and cost. While context compression offers a potential remedy, prior approaches suffer from static pruning strategies and granularity mismatches, often failing to preserve the semantic dependencies and syntactic details crucial for SE tasks. To strictly preserve critical task evidence whil

Read original source ↗ Open in workspace

recordType

paper

region

Global