slay the spire 2 agents went 0 wins to 60% after killing the chat log
researchers replaced growing chat logs with structured memory, allowing agents to win slay the spire 2 60% of the time, proving context management matters more than model size.
frontier models failed 100% of attempts at slay the spire 2, but the agenticsts architecture achieved a 60% win rate by discarding chat logs in favor of structured memory slots. the system uses five layers—protocol, state, rules, run summaries, and skills—to rebuild the prompt for each decision without context bloat. this approach proved that episodic learning and skill libraries are more critical than raw model power for complex planning tasks.