Agentsensus：多智能体故事世界的共识压缩共享记忆
Agentsensus: Consensus-Compressed Shared Memory for Multi-Agent Story Worlds
浏览论文内容
中文总结 AI 辅助
针对多智能体故事世界每角色私有记忆导致的存储重复问题，提出Agentsensus框架，通过统一长时记忆合并共享事件并链接相关记录，减少22-44%写入，实现14-28%共享与94-99%链接，且模拟质量不降。
中文摘要 AI 辅助
智能体故事世界是一个动态系统，模拟谁学到了什么、何时学到以及从谁那里学到——但标准设计赋予每个角色一条私有记忆流。因此，一个共享事件会为每个目击者存储一次，在存储方面将产生大量重复。我们提出Agentsensus，一个故事世界模拟框架，其中有一个统一的长时记忆。同一事件的记录合并为由其所有目击者共同拥有的一条记录，并且语义相关的记忆记录被链接起来。我们在四个世界上进行评估——两部中国古典小说、《哈姆雷特》以及一个真实世界的冲突时间线——在同等粒度协议下，针对三种每角色记忆设计，运行40到80轮。Agentsensus比最接近的基线少写入22-44%的条目，并且是唯一一种记忆变得共享（14-28%的记录由多个角色持有，有些由10个角色持有）和链接（94-99%）的设计，其模拟质量经评判与基线相当甚至更好。一项消融研究将此归因于合并本身：禁用合并会使存储量增加3.1倍，并将共享率降至恰好为零。共享还会随视野长度复合增长而非早期饱和，当一个世界分别以10、20和40轮重新运行时，共享率从6%升至9%再升至14%。
英文摘要
A agentic story world is a dynamic system simulating who learned what, when, and from whom -- yet the standard design gives each character a private memory stream. A shared event is therefore stored once per witness, large duplication will be incurred in terms of storage. We present Agentsensus, a story-world simulation framework in which there is an unified long-term memory. Records of the same event merge into one owned by all its witnesses, and semantically relevant memory records are linked. We evaluate on four worlds -- two classical Chinese novels, Hamlet, and a real-world conflict timeline -- run for 40 to 80 rounds against three per-character memory designs under an equal-granularity protocol. Agentsensus writes 22-44% fewer entries than the closest baseline and is the only design whose memory becomes shared (14-28% of records held by more than one character, some by 10) and linked (94-99%), at judged simulation quality indistinguishable or even better than the baselines. An ablation attributes this to the merge itself: disabling it multiplies the store by 3.1x and takes sharing to exactly zero. Sharing also compounds with the horizon rather than saturating early, rising 6% to 9% to 14% as one world is re-run at 10, 20 and 40 rounds.
