Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from 0.455 to 0.05 across stages, while MultiWOZ shows 78.2% accuracy with 6.8% false memory rate under persistent retention. This work introduces an adaptive budgeted forgetting framework that regulates memory through relevanceguided scoring and bounded optimization. The approach integrates recency, frequency, and semantic alignment to maintain stability under constrained context. Comparative analysis demonstrates improved long-horizon F1 beyond 0.583 baseline levels, higher retention consistency, and reduced false memory behavior without increasing context usage. These findings confirm that structured forgetting preserves reasoning performance while preventing unbounded memory growth in extended conversational settings.

翻译：长时域对话智能体需要持久记忆以进行连贯推理，但无控制的积累会导致时间衰减和错误记忆传播。LOCOMO和LOCCO等基准测试报告显示，各阶段的性能从0.455下降至0.05，而MultiWOZ在持久保留策略下准确率为78.2%，错误记忆率为6.8%。本文提出一种自适应预算驱动遗忘框架，通过相关性引导评分和有界优化来调节记忆。该方法整合了时效性、频率和语义对齐，以在受限上下文下维持稳定性。对比分析表明，该框架在长时域F1分数上超越0.583的基线水平，具有更高的保留一致性，且在不增加上下文占用的情况下减少了错误记忆行为。这些发现证实，结构化遗忘机制能够在扩展对话场景中保持推理性能，同时防止记忆的无限制增长。