Long-running AI agents accumulate episodic logs that quickly outstrip any practical context window. We study memory consolidation: the periodic compression of raw episodic logs into a smaller set of durable, retrievable memory atoms.
We introduce the Context Decay Benchmark, a reproducible simulation framework for evaluating how agentic harnesses manage information over long conversations. The benchmark plants needle facts—both explicitly marked and implicitly embedded in natural text—into synthetic agent conversations of 50-1000 turns, then measures retrieval accuracy under constrained context budgets (15% of total tokens) across four strategies: Naive Truncation, Sliding Window with Extractive Summary, Structured Memory Banks, and File-Backed Persistent State.
Large language model (LLM) agents are increasingly deployed as long-running autonomous systems that persist across sessions, manage complex multi-step workflows, and interact with external tools over extended time horizons. However, the harness layer—the orchestration infrastructure that wraps the LLM and mediates its interaction with the environment—remains under-examined as a first-class architectural concern.
We present Memory Tiering, a dynamic three-tier memory management architecture for AI agents that classifies all agent memory into HOT (active session context), WARM (stable preferences and configuration), and COLD (long-term archive) tiers, each with distinct retention policies and pruning strategies. The skill provides an executable Organize-Memory workflow triggered automatically after compaction events or on demand.