AI agents win at Slay the Spire 2 after researchers replace growing chat logs with structured memory
The AgenticSTS project replaces the ever-growing chat log of AI agents with five separate memory layers. Tested on the card game Slay the Spire 2, the prompt stays at around 5,000 tokens instead of ballooning past 500,000.
How much of its past conversation should an AI agent even see when it’s chasing a goal across hundreds of decisions? The AgenticSTS project, built at Alaya Lab with Shanghai Jiao Tong University and other institutions, flips the usual answer. The agent never sees its own chat log but instead rebuilds each decision from a fixed catalog of neatly organized information. The researchers picked the deck-building roguelike Slay the Spire 2 as their test bed. A single playthrough involves hundreds of decisions, from picking cards and planning fights to choosing routes on the map and buying items. The rules translate fully into text, randomness is high, and runs are long. Human players win 16 percent of the time on the lowest difficulty level, A0, according to the developers. Frontier models used in the AGI-Eval assessment didn’t win a single game across five tested setups. The game is hard but open-ended enough that architectural differences show up clearly. Typical LLM agents like ReAct or Reflexion append past observations, tool calls, and self-reflections to the next prompt. The context grows with every step until the window overflows or the model’s attention gets diluted. AgenticSTS does the opposite. For each decision, the prompt is freshly built from five clearly separated slots. L1 holds fixed protocol instructions, L2 holds state schemas with currently valid actions, L3 holds retrieved game rules, L4 holds summaries of previous runs, and L5 holds strategy skills triggered for specific situations. Anything the agent wants to carry over from a prior decision must first be written into one of these storage areas.
