Draft-OPD introduces an on‑policy distillation method for speculative draft models, addressing the mismatch between supervised fine‑tuning and inference by letting the target model supervise the drafter on draft‑induced states. The approach uses target‑assisted rollouts for stable continuations and replays drafting from error positions exposed during verification, enabling the drafter to learn from both accepted and rejected proposals. Experiments demonstrate that Draft‑OPD achieves more than five‑fold lossless acceleration across diverse tasks, outperforming prior draft models such as EAGLE‑3 and DFlash by 23 % and 13 % respectively.
By Haodi Lei, Yafu Li, Haoran Zhang, Shunkai Zhang, Qianjia Cheng, Xiaoye Qu, Ganqu Cui, Bowen Zhou, Ning Ding, Yun Luo, Yu Cheng
arXiv:2610.19185v1 Announce Type: new
Abstract: Evaluation of large language models (LLMs) remains largely pre-scientific: it involves many design decisions, with little guidance on how to make them....
By Shenbin Qian, David Samuel, Jind\v{r}ich Helcl, Andrey Kutuzov, Stephan Oepen
arXiv:2609.38096v1 Announce Type: new
Abstract: Policies with similar mean returns can differ sharply in rare failures, yet estimating lower-tail conditional value-at-risk (CVaR) accurately can requi...
By Pauline Bourigault, Xiaotong Ji, Matthieu Zimmer, Rasul Tutunov, Haitham Bou-Ammar
The paper introduces the Expected Decoding Rounds (EDR) objective, a theoretical framework that models speculative decoding as a Markov reward process and directly optimizes the number of decoding rounds. EDR weights local rejection costs by state occupancies, eliminating auxiliary hyperparameters and enabling unbiased stochastic optimization via temporal‑difference gradients. Applying EDR to fine‑tune state‑of‑the‑art draft models (DSpark and DFly) improves mean accepted length and outperforms prior training objectives across nine benchmarks in math reasoning, code generation, and chat.
By Yunxiao Zhao, Changxiao Cai
arXiv:2607. 27283v1 Announce Type: new Abstract: Long-horizon benchmarks often show that agents fail more as tasks become longer.
By Chao Peng, Zhiheng Lyu, Peijie Dong, Hande Dong, Qiang Lin
arXiv:2609.37169v1 Announce Type: cross
Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since add...
By Zhehao Huang, Changxin Tian, Qingyuan Yang, Kunlong Chen, Ziqi Liu, Zhiqiang Zhang, Xiaolin Huang, Jun Zhou