• Computer Science > Computation and Language [Submitted on 4 Feb 2026] Title:Budget-Aware Agentic Routing via Boundary-Guided Training View PDF HTML (experimental)Abstract:As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable • While model routing is effective for single-turn queries, agentic routing is a sequential, path-dependent problem: early mistakes compound, feedback is often at the end of the episode, and deployments often demand strict per-task spending limits • We propose Budget-Aware Agentic Routing, which selects between a cheap and an expensive model at each step to optimize the cost–success frontier and to operate under strict per-task budgets • We propose Boundary-Guided Training, which leverages two boundary policies (always-small vs • \ always-large) to build a difficulty taxonomy and to anchor learning under sparse rewards • Our approach warms start with boundary-guided SFT data synthesis via stratified sampling of cost-efficient trajectories, then applies Boundary-Guided Policy Optimization (BoPO), combining boundary-relative rewards with a ref

Article Summaries:

  • Computer Science > Computation and Language [Submitted on 4 Feb 2026] Title:Budget-Aware Agentic Routing via Boundary-Guided Training View PDF HTML (experimental)Abstract:As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable. While model routing is effective for single-turn queries, agentic routing is a sequential, path-dependent problem: early mistakes compound, feedback is often at the end of the episode, and deployments often demand strict per-task spending limits.

Sources: