这篇论文提出MAA，能让智能体自我进化时跨批次累积有效操作，减少75%的token消耗，在多个基准上超过现有方法。
现有批量式轨迹蒸馏中，同一记忆操作在不同批次间可能收到矛盾反馈，缺乏跨批次操作级证据累积机制。MAA通过构造差分信号使证据跨批次可比，利用指数移动平均累积每操作符号证据，并通过语义身份合并保证跨批次可追溯。在4个基准和4个目标模型的16个设置中，MAA取得14个最佳结果，一致优于现有批量级蒸馏基线。优化阶段token消耗减少约75%。
Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution
In batch-style trace distillation, the same memory operation may receive contradictory feedback across different batches. Existing methods lack a cross-batch, operation-level evidence accumulation mechanism, making it impossible to distinguish stably effective operations from accidental hits. This paper formalizes the requirement as two structural conditions, alignability and comparability, and proposes Marginal Advantage Accumulation (MAA). MAA constructs differential signals to make them comparable across batches, accumulates signed evidence per operation via EMA, and ensures cross-batch traceability through semantic identity merging. As a post-processing architecture, MAA achieves the best results in 14 out of 16 settings across 4 benchmarks and 4 target models, consistently outperforming existing batch-level distillation baselines and matching or surpassing online alternatives in most settings, while reducing optimization-phase token consumption by approximately 75%.