More Is Not Always Better: Overlapping Gains and Composition Failures in Agent Adaptation

Language-model agents can adapt through reflective instructions, retrieved memory, and weight updates. Should combining useful channels improve performance? We study this question with a frozen $2^3$ factorial design, reversed presentation order, and matched token allowances. On 77 held-out coding tasks with Qwen3-8B, 1,386 condition records from 1,232 distinct generations yield no Holm-corrected interaction in either the primary analysis or a grading-replay sensitivity analysis. The primary reflection–memory interaction is $-7.79$ percentage points. A task-level audit separates four overlapping-gain cases, where both individual channels and their combination succeed, from three observed combination-damage cases. Adding memory to reflection rescues two tasks and loses two others, leaving the total unchanged. Thus equal scores can hide changes in solved tasks, and a negative interaction estimate alone does not identify destructive interference. An exploratory 270-generation study on reused validation tasks does not establish a benefit from targeted transformation checks. We then test composition decisions on 169 new tasks with 845 generations: a development-fitted, outcome-blind router passes 47 tasks versus 42 for the development-selected fixed combination ($+2.96$ points; Holm $p=0.25$). Reducing memory from three items to one passes 44 versus 42 ($+1.18$ points; Holm $p=0.82$). Evaluation errors remain material: 36 records after replay in the factorial study, 20 in the exploratory study, and 81 in the new-task study. Our evidence distinguishes overlapping benefits from observed composition failures and connects diagnosis to prospective selection tests, while leaving robust antagonism, ordering advantages, and reliable adaptive composition unconfirmed.