@inproceedings{wang-etal-2026-guided,
    title = "Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding",
    author = "Wang, Juncheng  and
      Hu, Zhe  and
      Xu, Chao  and
      Ren, Siyue  and
      Feng, Yuxiang  and
      Liu, Yang  and
      Sun, Baigui  and
      Wang, Shujun",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.138/",
    pages = "3005--3018",
    ISBN = "979-8-89176-380-7",
    abstract = "Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts{---}especially those describing complex sound events. We uncover a surprising capability in AR audio generators: their early prefix tokens implicitly encode global semantic attributes of the final output, such as event count and sound-object category, revealing a form of implicit planning. Building on this insight, we propose Plan-Critic, a lightweight auxiliary model trained with a Generalized Advantage Estimation (GAE)-inspired objective to predict final instruction-following quality from partial generations. At inference time, Plan-Critic enables guided exploration: it evaluates candidate prefixes early, prunes low-fidelity trajectories, and reallocates computation to high-potential planning seeds. Our Plan-Critic-guided sampling achieves up to a 10 points improvement in CLAP score over the AR baseline{---}establishing a new state of the art in AR text-to-audio generation{---}while maintaining computational parity with standard best-of-N decoding. This work bridges the gap between causal generation and global semantic alignment, demonstrating that even strictly autoregressive models can plan ahead."
}