AI/ ai · llm · context-management · research

LLMs That Manage Their Own Memory

A new system called Self-GC lets long-running AI agents govern their own context like a garbage collector, cutting token use without losing critical state.

Long-running AI agents now have a smarter way to forget.

Researchers have proposed Self-GC, a context management system for large language model agents that handle extended, multi-step tasks. Instead of relying on blunt heuristics — like dropping the oldest messages or summarizing everything near a context limit — Self-GC treats each user turn, tool result, and skill state as an indexed object with a lifecycle. A side-channel planner proposes what to fold, mask, or prune; a harness enforces those decisions while keeping recoverable copies. The result: the agent sheds dead weight without accidentally discarding something it will need later.

The numbers are meaningful. On a 33-session hard test set, Self-GC pruned 43.95% of prefix tokens while leaving 84.85% of future continuations unaffected — well above the 54.55% to 69.70% no-impact rates from heuristic baselines. On a larger 332-session production-derived suite, the system reached no-impact rates of 91.27% to 94.58%, versus 77.71% to 87.46% for baselines. In a live online split, it cut daytime average input tokens by 10% to 15%, with peaks near 20%.

Context windows have grown enormous — Gemini 1.5 and others now offer millions of tokens — but raw capacity doesn't solve the problem of what to do with a sprawling agent state mid-task. Stuffing everything in and hoping the model attends to the right parts is expensive and error-prone. Self-GC is a bet that agents need runtime lifecycle control, not just a bigger bucket.

Self-governing memory sounds appealing until you remember that the planner deciding what to prune is itself an LLM — so the system's reliability ultimately rests on one model trusting another to not throw away the wrong thing.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →