AgenticSTS：一种面向长程LLM智能体的有界记忆测试平台

摘要

针对长周期大语言模型代理的记忆，本质上是一份关于每个未来决策可访问内容的契约。最简单的契约是将过去观测、工具调用和反思内容附加到每次提示中——这种方式虽便于获取历史上下文，但会导致信息混杂，难以单独分析某个记忆组件的影响。我们提出并实施了一种替代性受限契约：每次决策都由基于类型检索生成的独立用户消息驱动，不再附加原始跨决策记录。这使得提示内容在任意长度的运行中保持受限，且任一记忆层可被独立消融。我们在《杀戮尖塔2》中验证了该契约——这是一款规则闭合的随机卡牌构筑游戏，单次运行需数百次战术与战略决策。现有前沿大语言模型在相同游戏上的公开基准测试显示，五种配置下最低难度的胜率均为0%，而开发者报告的人类在相同难度下的胜率为16%；该任务具有挑战性但尚未饱和。在我们的测试框架中，固定A0消融实验显示，当启用触发式战略技能层时观测到最大差异：无存储基线胜率3/10，添加技能层后提升至6/10。该样本规模下的比较仅具方向性而非统计显著性（费希尔精确检验p≈0.37）；跨骨干网络探测与公共累积上下文基线作为操作性比较报告，而非针对契约变量本身的控制测试。我们发布了一个可复现测试平台：包含298条已完成轨迹（附条件标签）、冻结记忆/技能快照、提示记录及分析脚本——这是一套代理设计方案以及经过验证的、可复用的方法论，用于研究显式记忆层如何塑造长周期大语言模型代理的决策行为。

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.