Agent-Conditioned Routing: Diverse Reasoning Paths Within One Frozen Model

Agent-Conditioned Routing (ACR) is a technique that enables a frozen sparse mixture-of-experts model to generate diverse reasoning paths from a single prompt without fine‑tuning or user‑assigned roles. By assigning persistent, untrained expert‑eligibility masks while keeping the model’s token router intact, ACR produces more problems with at least two distinct primary methods compared to temperature sampling on GLM 5.3 and GPT‑5.6 Sol. ACR adds minimal overhead (≈160 KiB) and maintains latency and VRAM usage within 3% of standard sampling.

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
• fine-tuning
• benchmarks