Tool‑using LLM agents spend wall‑clock time not only on model inference but also in serial action‑observation turns, where each tool call, environment transition, and observation can delay subsequent decisions. We introduce Speculative Macro Commit (SMC), a runtime mechanism for a two‑tier agent system: a large authoritative actor model produces the official trajectory, while a faster speculative drafter model continuously predicts and executes future action chains on an isolated environment snapshot. SMC mines recurring multi‑action skeletons from training traces, stores them in a macro library, and matches them against action chains predicted by the drafter at runtime. When the actor’s next tool call matches the first drafted action, SMC commits the remaining pre‑executed draft steps together with their observations to the official trajectory. Experiments use Qwen3.5‑27B INT4 as the authoritative actor and Qwen3.5‑4B as the drafter. Compared with the Speculative Actions (SA) baseline, SMC reduces overall latency by 10.23% on the $$\tau^2$$‑Bench Telecom subset and by 18.59% over sequential execution; on AppWorld it reduces wall time by 7.7% over the SA baseline and by 44.9% over sequential execution, with a slight drop in task completion. SMC provides a practical way to reuse multi‑step speculative execution beyond single‑step speculative actions. Code is publicly available at https://github.com/zeyuliu1037/speculative-macro-commit.
Review