arXiv cs.AI· Emile Anand, Mohammed Rehan Parwani, Xinyuan Cao·· 12 小时前AI 评分34
自适应多 Token 预测（AMTP）：推测窗口该走多远？
Adaptive Multi-Token Prediction: How far should we go?
AI 导读
研究者提出自适应多 Token 预测（AMTP），用轻量控制器在每轮起草前预测草稿前缀的接受存活概率，并选择每秒期望 Token 数最高的推测窗口，无需重训模型、不改动验证器。
正文 · 原文
Abstract:Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. However, the best speculation horizon changes with context: longer drafts offer greater amortization when reliable, but can waste compute on suffixes discarded after a rejection. Unlike autoregressive drafting, where a stopping rule can decide token by token, MTP must fix the horizon before drafting, as all heads fire in the same forward pass. We therefore formulate horizon selection as an online control problem, using verification feedback to learn how far the draft can be trusted in each context, and introduce Adaptive Multi-Token Prediction (AMTP): a lightweight controller that requires no retraining and leaves the exact verifier unchanged. To guide horizon selection, we characterize the expected number of tokens committed at each horizon via acceptance survival, the probability that a draft prefix is fully accepted. Before each round, AMTP predicts how far the draft is likely to survive and picks the horizon with the highest expected tokens per second, learning freely from every verification pass. Theoretically, we show that any online learner's prediction error translates into throughput regret against the best horizon for each context, and in turn into a bound on wall-clock completion time. With online gradient descent, this regret is sublinear. Across five draft-target pairings built on Llama-3.1-8B-Instruct with Medusa heads, Meta's MTP models, and Qwen3-4B-Inst-2507-MTP, evaluated on AIME 2025 and GSM8K, AMTP decodes up to 4.1x faster than standard decoding and matches or outperforms the fixed window in 8 of 10 settings, with throughput gains of up to 10%.
| Comments: | 25 pages, 5 figures, 9 tables |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY) |
| ACM classes: | I.2.6; I.2.7; I.2.8 |
| Cite as: | arXiv:2610.28619 [cs.AI] |
| (or arXiv:2610.28619v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28619 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mohammed Rehan Parwani [view email]
[v1]
Tue, 20 Oct 2026 17:56:32 UTC (655 KB)
来源：arXiv cs.AI · arxiv.org