SPADE: Self-Play in Adaptive Synthetic Executable Environments

Key points

SPADE makes environment design itself a learnable component. The distribution of environments produced by the designer coevolves with the agent's capabilities.
A hint-based regret signal is the key mechanism. A purely adversarial designer proposes unsolvable tasks, while a purely cooperative designer proposes tasks with nothing to teach. The performance gap with and without hints automatically targets environments that are both feasible and worth learning from.
Because each environment is written as executable code with a Gym-style interface, one interface can cover both single-turn reasoning problems and multi-turn tool-use tasks.
Grounding the designer in documents from a pretraining corpus and maintaining an accumulated memory of previously created environments were both critical to performance.
At the 30B scale, SPADE improves over the strongest fixed-environment baseline by an average of 5.3 points across eight mathematics, science, coding, and reasoning benchmarks, by 5.7 points on BFCL v4 multi-turn, and by 13.9 points on ACEBench-Agent.

External research summaries. These are not HDATF publications or measured product results.