Learning to Configure Agentic AI Systems

The paper introduces ARC, a lightweight hierarchical policy that learns to configure LLM‑based agent systems on a per‑query basis by treating each configuration as a temporally extended option in a semi‑Markov decision process. Unlike fixed templates or hand‑tuned heuristics, ARC dynamically selects workflows, tools, token budgets, and prompts tailored to the difficulty of each query. Experiments on reasoning, tool‑use, and agentic benchmarks show that ARC outperforms budget‑matched tool‑augmented LLMs, boosting reasoning accuracy by 31.3%, tool‑use accuracy by 13.95%, and doubling success on the τ‑Bench Airline Pass task from 9.0% to 18.0%.

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.

• llms
• agents
• reinforcement-learning
• benchmarks