Interference-Induced Forgetting in Co-Trained Multi-Agent Language Models: Comparing Weight Coupling with Explicit Memory

Multi-agent language systems compose specialized roles, including solvers, verifiers, and extractors, whose interactions can change as collaborating agents drift. We define interference-induced forgetting (IIF) as task-grounded reliability loss in a fixed receiving agent following drift in messages from one or more collaborators, under a fixed task and evaluation contract. This role-level construct is not restricted to two-agent teams; the empirical results here concern specific solver-verifier and solver-extractor systems. A validity gate is necessary for measuring IIF, while interface-specific attribution also requires controls for source capability and evaluation-path changes. In early Qwen3-4B GSM8K natural-drift trials, verifiers approved over $99.5\%$ of outputs and matched the always-approve baseline, so those trials fail the gate and do not establish IIF. An exploratory seed-42 reward-targeting endpoint paired proxy-reward gain $+1.756$ with $\Delta$AUC $-0.194$, but the three-seed audit found no significant paired AUC contrast and imperfectly matched policy movement. The answer-present extractor showed no significant conditional-fidelity degradation. Under partner substitution, episodic critique, semantic rubric and hybrid memory each improved endpoint accuracy over zero-shot across five benchmarks; hybrid achieved $93.95\%$ mean relative endpoint accuracy across eight GSM8K/MATH-500 cells