Structured Memory Helps Agents Win Games
The Decoder · rss · 2026-07-12
The Decoder reported on an AI agent memory management study: researchers replaced ever-expanding chat logs with a 5-layer structured memory, allowing agents to avoid stuffing their entire history into the prompt during long tasks.
They tested this AgenticSTS approach on Slay the Spire 2. Results showed that prompt length remained stable at around 5,000 tokens instead of ballooning to over 500,000 tokens. Out of 10 test games, the agent using structured memory won 6 games, while the control group won none.
More from coding & agent
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11