Beyond Current-Task Success: Revision Sufficiency for Learning Agents

Agents compress experience into reusable strategies for the objective at hand. A strategy that improves current execution may nevertheless become inadequate when the success criterion changes. We study *revision sufficiency*: whether a retained representation supports behavior under a specified revised criterion, without additional adaptation episodes before held-out evaluation. On procedurally generated tool-use tasks, we compare a trajectory archive with a strategy built from the same evidence for the original objective. Planning and execution are matched across representations within each stage. In a preregistered study of $600$ seeds with $507$ complete pairs, the strategy succeeds more often before revision ($99.2\%$ versus $89.2\%$) but $47.7$ percentage points less often afterward. A separate control constructs the strategy for the revised objective under the same length cap; it then outperforms both the original-objective strategy and the archive after revision. These results distinguish the immediate usefulness of goal-specific preprocessing from the ability to reuse experience under a changed objective. Current-task acceptance can favor the former without establishing the latter. This paper identifies an overlooked factor in long-running self-evolving agent systems.