DAEDALUS: Bootstrapping agent memory from self-generated tasks
An arXiv paper introduces DAEDALUS, a method that bootstraps reusable agent memory from self-generated practice without existing tasks or an oracle verifier. An explorer agent creates challenging but solvable tasks while a solver agent attempts them; heuristics derived from solver failures are accepted only after repeated in-context success, then consolidated into a memory bank. Across AppWorld, τ²-bench and AutomationBench, it improves mean success rates by up to 15.9 points and pass^5 by up to 2.2x over a no-memory baseline, at lower inference cost than most comparable methods.
It suggests agents can accumulate transferable operational know-how without human-written guidelines or verifiers, which could cut the trial-and-error cost of deploying agents in unfamiliar environments.