PreCoMem：面向自进化长期对话智能体的预测式记忆框架
PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
给长期对话智能体做记忆的可以看看，它不像老方法那样全量追加或硬覆盖，而是按置信度决定强化、暂存还是衰减，代码已开源。
arXiv 论文提出 PreCoMem，一个受预测编码启发的记忆整合框架，把用户记忆表示为带置信度的信念。核心信号 Effective Surprisal 结合语义偏差与矛盾证据，在检索不可靠时自动降权。两阈值门控将每轮对话映射为 MAINTAIN、PROFILE、CORRECT 三种确定性更新，其中 PROFILE 阶段充当缓冲区，避免过早采信噪声。在 LoCoMo、LongMemEval-S、PersonaMem-v2 三个基准上取得一致的 SOTA 准确率，新提出的 DiMoBench 验证其能适应非平稳的信念漂移而不对噪声过度反应。
PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
Long-horizon dialogue agents need to keep user memories stable enough for personalization while adapting when the user genuinely changes. Existing memory systems often append every observation or overwrite old entries by heuristic rules, which makes transient noise hard to distinguish from real belief drift. We introduce PreCoMem, a memory consolidation framework inspired by predictive coding that represents memory as confidence-weighted beliefs about the user's state. Its core signal, Effective Surprisal, combines semantic deviation and contradiction evidence, then downweights this signal when retrieval is diffuse and unreliable. According to effective surprisal, a two-threshold gate maps each turn to one of three deterministic updates: MAINTAIN reinforces supported beliefs, PROFILE stores ambiguous cues as low-confidence hypotheses, and CORRECT softly decays reliably contradicted facts. The PROFILE stage acts as an explicit waiting room, preventing premature commitment to noisy evidence. Experiments on LoCoMo, LongMemEval-S, and PersonaMem-v2 show consistent state-of-the-art accuracy; our new DiMoBench confirms that PreCoMem adapts to non-stationary belief drift without over-reacting to noise. The code is available at https://github.com/ZhongWishing/PreCoMem.