developer tools
Equal Token Budgets Delivered Unequal Memory
A coding-agent study separates stored state, delivered context, management work and task outcome instead of treating memory as one number.
Summary
A coding-agent study separates stored state, delivered context, management work and task outcome instead of treating memory as one number.
Across 55 archived coding-agent trajectories, instructions, artifacts, tool outputs and agent-generated state showed different retention and compression patterns. Object-aware compression and retrieval policies exposed a second problem: gains calibrated on one set of tasks did not necessarily transfer, while nominally equal token budgets hid differences in delivered context and management cost. A real-system replay surfaced serving limits as well. The evidence is a focused trajectory study, but it argues for measuring memory by semantic role and operational effect.
Why it matters
A coding-agent study separates stored state, delivered context, management work and task outcome instead of treating memory as one number.
Limits and context
- Object-aware compression and retrieval policies exposed a second problem: gains calibrated on one set of tasks did not necessarily transfer, while nominally equal token budgets hid differences in delivered context and management cost.
Key claims
A coding-agent study separates stored state, delivered context, management work and task outcome instead of treating memory as one number.
Qualification: Object-aware compression and retrieval policies exposed a second problem: gains calibrated on one set of tasks did not necessarily transfer, while nominally equal token budgets hid differences in delivered context and management cost.
Evidence: source-2026-09-01-006
Sources
- arXiv preprint 2608.31057arXiv · primary research
Corrections
No corrections have been recorded for this story.