Kunjun Li, Wenhao Chai, Yihao Liang, Yuezhou Hu, Shuyao Xu, Yi Pan, William X. Zheng, Kannan Ramchandran 等 10 位作者
Speculative decoding accelerates memory-bound LLM decoding with a lightweight drafter, and parallel drafters extend this speedup by drafting a whole block in one forward pass. However, it remains unclear whether their released systems (stock) attain the full speedup that parallel drafting permits. We identify three challenges. First, with one request, each step accepts few tokens but reads every target weight. Second, with batching, per-request verification work roughly halves the speedup over autoregressive (AR) decoding. Third, speculative decoding is deployment-specific, and no universal optimization fits every serving regime, drafter, target model and GPU. To address these challenges, we present SpecPilot, an autonomous agentic loop that discovers algorithms and systems optimizations for each deployment. In each round, a cost model locates the largest gaps between the current system and its ceiling. Parallel agents explore directions and integrate the successful ones. Token forcing checks every output token against stock to detect reward hacking. A structured memory carries validated mechanisms to new rounds and deployments. SpecPilot discovered a general lossless 12-bit weight format, tree verification for hybrid recurrent targets, two-level verification and three batching mechanisms. We evaluate it across four target models, three drafters, two GPU platforms and five benchmarks. Without training or quality loss, it raises the speedup over AR from stock's 4.46$\times$ to 10.87$\times$ with one request, and from 1.94$\times$ to 3.93$\times$ with batching.
Shuyao Xu University of Virginia and National University of Singapore, Cheng Peng, Jiangxuan Long University of Hong Kong, Weidi Xu Infly Technology, Wei Chu Inf Tech, Yuan Qi Fudan University
Recent advances in model distillation show that data from advanced reasoning models can effectively train smaller student models. However, standard practices discard incorrect reasoning traces—valuable, yet underutilized data. This paper addresses the critical question: How can both positive and negative distilled reasoning traces be effectively leveraged to maximize LLM reasoning performance in an offline setting? We employ a two-stage training recipe: first, Supervised Fine-Tuning (SFT) on positive traces, followed by a refinement stage using both positive and negative traces. We find that a simple REINFORCE-style objective, which we term the Reinforcement Distillation (REDI) objective, outperforms established preference optimization methods like DPO and SimPO in this distillation context. Our empirical evaluations demonstrate the effectiveness of this approach. Notably, our Qwen-REDI-1.5B model, trained on just 131k traces from the open Open-R1 dataset, achieves an 83.1% score on MATH-500. Its performance matches that of DeepSeek-R1-Distill-Qwen-1.5B, a model trained on 800k proprietary data. This result showcases the remarkable data efficiency of utilizing previously discarded negative traces.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表