@inproceedings{wang-etal-2026-conma,
    title = "{C}on{MA} : Confidence-Guided Kernel Sampling with Multi-Stage Aggregation for {LLM} Reasoning",
    author = "Wang, Yinuo  and
      Li, Qingjie  and
      Cui, Wenyao  and
      Li, Qiuchi  and
      Huaping, Zhang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1475/",
    pages = "29500--29518",
    ISBN = "979-8-89176-395-1",
    abstract = "Test-time scaling (TTS) enhances LLM reasoning capabilities by sampling and aggregating diverse solution trajectories. However, existing approaches often rely on external verifiers and one-shot independent sampling, which results in inefficient budget allocation and underutilizes interim high-quality trajectories. We propose ConMA, a training-free, verifier-free TTS framework that reallocates a fixed inference budget into iterative sample{--}filter{--}diversify{--}select cycles: it filters answer groups based on intrinsic token-probability confidence, enriches candidates through diversity-aware expansion, and employs repeated single-choice selection for multi-stage refinement. Across multiple benchmarks, ConMA consistently improves accuracy under fixed budgets. With a maximum budget of N=64, ConMA boosts Qwen3-4B to 80{\%} accuracy on AIME25, significantly outperforming strong baselines while converging early with only 18 samples on average, substantially reducing inference cost."
}