Search papers, labs, and topics across Lattice.
DAEDALUS bootstraps reusable agent memory by pairing an explorer agent that generates self-supervised tasks with a solver agent that attempts them, deriving heuristics from solver failures and successes. This approach circumvents the need for human-written guidelines or pre-existing task sets with oracle verifiers, enabling agents to learn operational knowledge autonomously. Across multiple benchmarks, DAEDALUS significantly improves success rates and trajectory efficiency compared to memory-less baselines, demonstrating competitive performance with methods requiring prior task knowledge at reduced inference costs.
Agents can learn to act reliably in new environments by generating their own practice tasks and distilling reusable heuristics from self-identified failures, achieving significant performance gains without human supervision or pre-defined benchmarks.
LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own. Without memory of past attempts, they repeat the same mistakes across tasks, leading to more task failures and longer trajectories. To address this, agentic systems typically rely on human-written guidelines or on procedural memory built from training tasks and an oracle verifier, both of which require prior knowledge of the environment. We present DAEDALUS, a method for bootstrapping reusable agent memory from self-generated practice without existing tasks or oracle verifiers. DAEDALUS pairs two agents: an explorer that interacts with the environment to generate challenging yet solvable tasks, and a solver that attempts them. A heuristic is derived from each solver failure and accepted only after the solver repeatedly succeeds with that heuristic in context. These outcomes also provide feedback for the explorer to refine the difficulty of future tasks. Accepted heuristics are then consolidated into a memory bank for test-time use. Across AppWorld, $\tau^2$-bench, and AutomationBench, DAEDALUS improves mean success rates by up to 15.9 points and pass^5 by up to 2.2x over a no-memory baseline, and is competitive with methods using training tasks, at a lower inference cost than most. We show that performance gains already emerge with a small exploration budget, and that its heuristics also benefit agents from other model families. Our ablations further reveal that solver traces provide the key information needed to derive effective heuristics, while factorizing early discoveries makes exploration more cost-efficient. Beyond memory construction, we find that the tasks generated by DAEDALUS can serve as a proxy for benchmark tasks when ranking models by performance. Code and artifacts: www.github.com/illuin-tech/daedalus.
