SOURCE-LINKED INTELLIGENCE

Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles and exhibit different size, retention, and representation profiles. Recent work has begun to explore memory-management mechanisms that account for such heterogeneity. This work focuses on semantic heterogeneity and studies how it should shape the management and evaluation of working memory in coding agents. Across 55 archived coding-agent trajectories, we find that semantically different working-memory objects exhibit distinct retention and compr

Read original source ↗ Open in workspace

recordType

paper

region

Global