Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP/NEXTN) draft head under the assumption that the draft is negligibly cheap.
HARTS (Hybrid‑Attention RL over Tree Structures) is a new system that jointly plans microbatches, data‑parallel replica assignments, and microbatch‑slot schedules to efficiently train agentic reinforcement learning models with hybrid attention over arbitrary rollout trees. It uses prefix compression and a linear‑time algorithm for chunkwise linear attention to avoid recomputing shared prefixes, enabling activation recomputation and bounded state replay while preserving trajectory‑wise training benefits. In experiments on an Agentic RL workload derived from SWE‑bench tasks, HARTS delivers 4.81–4.87× speedups in forward, backward, and gradient computations across multiple parallel configurations, with numerical differences comparable to baseline self‑rerun variation and a similar reward trend over the first 120 training steps.
By Boyuan Meng (Ant Group, China), Peihua Bao (Ant Group, China), Hong Liu (Ant Group, China), Xiaowei Zhu (Ant Group, China), Chao Wang (Ant Group, China), Gen Li (Ant Group, China), Zhenxuan Pan (Ant Group, China)
arXiv:2607. 21535v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel.
By Alagappan Valliappan
BF1 is a deterministic block‑aligned dyadic sparse‑attention retrofit designed to reduce the cost of causal attention in long‑context transformers. It combines a small exact local neighborhood, a global first block, and logarithmically spaced historical blocks, achieving O(n log n) token interactions per layer with O(log n) communication depth. On an NVIDIA RTX PRO 6000 Blackwell GPU, BF1 outperforms dense attention for 2K–4K tokens and delivers up to a 10.91× prefill speedup at 32K tokens, while retrofitting eight of 28 Qwen3‑0.6B layers reduces first‑token latency by up to 15.3% at 32K tokens and yields the lowest perplexity among compared sparse and dense training protocols.
By Hina Dixit
arXiv:2607. 14952v1 Announce Type: new Abstract: A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment.
By Changhai Zhou, Kieran Liu, Yuhua Zhou, Qian Qiao, Jun Gao, Harry Zhang, Irvine Lu, Nolan Ho, Lucian Li, Andrew Lei, Cleon Cheng, Steven Chiang, Yihang Zeng, Di Zhang, Rio Yang, Kaijie Chen, Andrew Chen, Pony Ma, Weizhong Zhang, Cheng Jin
arXiv:2608. 19758v1 Announce Type: new Abstract: Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase.
By Qihang Fan, Huaibo Huang, Zhiying Wu, Bingning Wang, Ran He