AgenticSTS：面向長週期LLM智能體的有界記憶測試平台

摘要

对于长时程LLM智能体而言，记忆是一份合同，规定了每个未来决策允许看到的内容。最简单的合同是将过去的观察记录、工具调用和反思内容附加到每个提示中，这使得先前上下文易于访问，但同时也使其变成一团混乱的混合物，导致任何单一记忆组件的影响都难以被分离。我们引入并实现了一种替代性的有界合同：每次决策均基于通过类型化检索组装的全新用户消息，不附加任何跨决策的原始记录。因此，提示在任意长度的运行中保持有界，任何单一层都可以被单独消融。我们在《Slay the Spire 2》中实例化该合同，这是一款规则封闭的随机卡牌构筑游戏，其每次运行需要做出数百个战术和战略决策。在同一游戏上对前沿LLMs的公开在线基准测试显示，在五组配置的最低难度下胜率为零；而开发者报告人类在相同难度下的胜率为16%；该任务困难但尚未饱和。在我们的实验框架内，固定A0的消融实验显示，当启用触发式战略技能时观察到的差异最大：无存储基线胜率为3/10，而添加技能层后胜率为6/10。在此样本量下，比较仅具方向性，而非统计上决定性（Fisher精确检验p≈0.37）；跨骨干网络的探测实验和公开的累积上下文基线作为操作性比较报告，而非对合同变量本身的受控测试。我们发布了一个可复现的测试平台：包含298条完整轨迹，附有条件标签、冻结的记忆/技能快照、提示记录和分析脚本——这是一种智能体设计，以及一种经过验证、可重复使用的方法论，用于研究显式记忆层如何塑造长时程LLM智能体的决策。

English

Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see. The simplest contract appends past observations, tool calls, and reflections to every prompt, which makes prior context easy to access but also turns it into a jumbled mixture in which the effect of any single memory component is hard to isolate. We introduce and instrument an alternative bounded contract: every decision is made from a fresh user message assembled by typed retrieval, with no raw cross-decision transcript appended. The prompt thus stays bounded across runs of any length, and any single layer can be ablated in isolation. We instantiate the contract in Slay the Spire 2, a closed-rule stochastic deck-building game whose runs require hundreds of tactical and strategic decisions. A public online benchmark of frontier LLMs on the same game reports zero wins at the lowest difficulty across five configurations, and the developer-reported human win rate at the same difficulty is 16%; the task is hard but not saturated. Within our harness, a fixed-A0 ablation shows the largest observed difference when triggered strategic skills are enabled: the no-store baseline wins 3/10 games and adding the skill layer 6/10. At this sample size the comparison is directional rather than statistically decisive (Fisher exact p\approx0.37); a cross-backbone probe and public accumulating-context baselines are reported as operational comparisons rather than controlled tests of the contract variable itself. We release a reproducible testbed: 298 completed trajectories with condition tags, frozen memory/skill snapshots, prompt records, and analysis scripts -- an agent design and a validated, reusable methodology for studying how explicit memory layers shape long-horizon LLM-agent decisions.