Paper Detail

AutoAdapt: Automatic Domain Discovery Enables Low-Cost Extensibility

Josh McGiff, Salma Mekaoui, Robert Shanahan, Nikola S. Nikolov

arxiv Score 3.8

Published 2026-10-07 · First seen 2026-10-08

General AI

Abstract

Instruction-tuned models are deployed into environments where domains are heterogeneous and evolve, yet adding new domains or data typically requires costly retraining. We present AutoAdapt, a modular framework that incorporates new domains and data via targeted single-adapter training without modifying other adapters. The framework automatically discovers latent domains, uses them to train per-domain Low-Rank Adaptation (LoRA) adapters independently in parallel and performs parameter-free routing. Across 14 domain-specific benchmarks and GPT-4o pairwise judgements, AutoAdapt achieves parity with a LoRA adapter trained on all domains without requiring full-model retraining. We also find evidence of specialisation effect convergence across independent discovery methods. Overall, training each adapter on its own domain prevents domain interference by construction, thus enabling modular, taxonomy-free domain specialisation without aggregate performance loss or full model retraining.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{mcgiff2026autoadapt,
  title = {AutoAdapt: Automatic Domain Discovery Enables Low-Cost Extensibility},
  author = {Josh McGiff and Salma Mekaoui and Robert Shanahan and Nikola S. Nikolov},
  year = {2026},
  abstract = {Instruction-tuned models are deployed into environments where domains are heterogeneous and evolve, yet adding new domains or data typically requires costly retraining. We present AutoAdapt, a modular framework that incorporates new domains and data via targeted single-adapter training without modifying other adapters. The framework automatically discovers latent domains, uses them to train per-domain Low-Rank Adaptation (LoRA) adapters independently in parallel and performs parameter-free routi},
  url = {https://arxiv.org/abs/2610.10349},
  keywords = {cs.LG},
  eprint = {2610.10349},
  archiveprefix = {arXiv},
}

Metadata

{}