titleAgentBaton: Efficient Model Collaboration in Agentic Tasks
authorsJunlong Li, Jindong Jiang, Yonggan Fu, Jiarui Yao, Hanrong Ye, Wonmin Byeon, Peter Belcak, Hao Zhang, Pavlo Molchanov
date2026-10-25
venuearXiv (preprint, not peer reviewed)
idarXiv:2610.35959
affiliationNVIDIA
upvotes19 (Hugging Face Daily Papers, 2026-11-11)
linksabs pdf hf
cite
relatedCosmos 3: Omnimodal World Models for Physical AI
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
abstractSolving long-horizon agentic tasks requires language agents to interact with their environments over multiple steps, and reliable performance often comes from the expensive capable models available through cloud providers. Meanwhile, alternative efficient models with inferior performance but a much lower cost are emerging, including lower-tier cloud models and smaller open-weights models deployable on local hardware. This raises a natural question that remains less explored than traditional query-level routing: can capable and efficient models collaborate within a single long-horizon agentic task to substantially reduce cost while preserving task accuracy? In this paper, we systematically investigate key design choices for such collaboration through model handoffs, where one model takes over from another, focusing on handoff direction and context transfer. We find that efficient-to-capable handoffs generally underperform capable-only execution with limited or even no cost reduction, whereas capable-to-efficient handoffs at suitable stages of task progress largely preserve or even improve accuracy while substantially reducing cost. These findings suggest that a one-time, simple, well-timed handoff strategy is good enough for cost-effective agent collaboration, motivating AgentBaton, a lightweight detector that learns when to hand off from recurring patterns in task progress. Across 11 model pairs and two representative benchmarks, AgentBaton reduces API costs by 65.9% on average while largely preserving task accuracy, with accuracy gains of up to 8.8 percentage points over capable-only execution. Experiments across various reasoning-effort settings further show that AgentBaton extends the empirical accuracy-cost Pareto frontier.

bibtex

@misc{li2026agentbaton,
  title={AgentBaton: Efficient Model Collaboration in Agentic Tasks},
  author={Junlong Li and Jindong Jiang and Yonggan Fu and Jiarui Yao and Hanrong Ye and Wonmin Byeon and Peter Belcak and Hao Zhang and Pavlo Molchanov},
  year={2026},
  eprint={2610.35959},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2610.35959}
}