Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents
arXiv:2610.21463v1 Announce Type: cross Abstract: Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps are routine enough for a much smaller model. Existing ways of sharing this work keep the strong model as the generator: routers and collaborative agents decide which model handles each query or step, and speculative methods check a small model's drafts one step at a time, usual…