Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks

The paper introduces WebMix, a mixture hypernetwork that enables web agents to adapt to unseen interfaces without retraining. WebMix uses a bank of pre‑trained low‑rank adapters and a scout agent that explores a new interface, summarizing observations into a manual. A lightweight router then predicts mixing coefficients to combine the adapters into a new one, achieving performance that matches or surpasses in‑context learning and LoRA baselines on domain and version transfer tasks.

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 Machine Learning.

• llms
• agents
• fine-tuning