AgentBaton: Efficient Model Collaboration in Agentic Tasks

AgentBaton explores how capable and efficient language models can collaborate on long‑horizon agentic tasks by handoffs, where one model takes over from another. The study finds that handoffs from a capable to an efficient model at appropriate stages preserve or improve accuracy while significantly cutting cost, whereas the reverse handoff is less effective. AgentBaton, a lightweight detector, learns the optimal handoff point and achieves an average API cost reduction of 65.9% across 11 model pairs while largely maintaining task accuracy, even gaining up to 8.8 percentage points over capable‑only execution.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• benchmarks