Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-07-25 · high
Facts kept only in conversation vanished at the first compaction and stayed missing through 106 of 108 later summaries.
Why now: As of July 25, the findings run counter to the assumption behind most agent memory tools: that they'll get used voluntarily.
A coding agent made zero memory calls across 114 turns despite a pre-seeded memory store, per a new evaluation from researcher Swapnanil Saha. That's a problem for any harness built around a recall tool. The design assumes the agent will ask for a fact when it needs one, and this run never did.
Saha's argument: memory can't be a document an agent opens on its own. It has to be a harness property, delivered whether the agent asks or not.
Saha ran a decay probe with ten facts held only in conversation, no harness backup. Every one vanished at the first compaction summary and stayed missing through 106 of 108 later compact-resumes.
The deprived agent's workaround was grepping the harness's own session files to rebuild what it had lost.
The fix that worked was deterministic, cue-triggered injection: facts pushed into context on a trigger instead of fetched by choice. That delivered in every seeded run with zero false alarms, and harness-injected facts survived all 138 compact-resumes tested.
Injection isn't free. Saha also measured that 39% of intra-session re-reads paid again for content the agent already had before a compaction boundary. That's redundant spend even when the memory system works exactly as designed.
Anyone wiring memory into a harness should design for push, not pull.
Each link below shares sources, entities, or timing with this story.
Shared entity: Coding / Same source domain / Shared topic / Earlier coverage
Both cover Coding; reported by the same outlet (arxiv.org); overlapping topics (agent, argu, coding, harness).
Both cover Coding; reported by the same outlet (arxiv.org); overlapping topics (agent, call, coding).
Shared entity: Harness / Shared topic / Earlier coverage / Tension
Both cover Harness; overlapping topics (agent, coding, harness); earlier Harness coverage from 2026-04-01.
Shared entity: Coding / Same source domain / Shared topic / Earlier coverage
Both cover Coding; reported by the same outlet (arxiv.org); overlapping topics (agent, coding).
Both cover Coding; reported by the same outlet (arxiv.org); overlapping topics (agent, coding).
Both cover Coding; reported by the same outlet (arxiv.org); overlapping topics (agent, coding).
Shared entity: Coding / Shared topic / Earlier coverage / Tension
Both cover Coding; overlapping topics (agent, argu); earlier Coding coverage from 2026-07-21.
Shared entity: Harness / Shared topic / Earlier coverage
Both cover Harness; overlapping topics (agent, coding, harness); earlier Harness coverage from 2026-04-13.