Speculative Macro Commit (SMC) is a runtime technique for tool‑using language‑model agents that separates an authoritative actor model from a faster speculative drafter model. The drafter predicts and executes future action chains on a snapshot, storing recurring multi‑action patterns in a macro library. When the actor’s next tool call aligns with a drafted action, SMC commits the pre‑executed steps, reducing latency by up to 18.59% on certain benchmarks while maintaining accuracy.
By Zeyu Liu, Souvik Kundu, Peter A. Beerel
Speculative Macro Commit (SMC) is a runtime technique that speeds up tool‑using language‑model agents by having a fast speculative drafter model predict and execute future action chains on a separate environment snapshot. The drafter’s predictions are matched against a macro library of recurring multi‑action skeletons; when the authoritative actor’s next tool call aligns with the first drafted action, SMC commits the remaining pre‑executed steps to the official trajectory. Experiments with Qwen3.5 models show that SMC maintains overall accuracy while cutting latency by up to 18.6% on telecom benchmarks and 44.9% on AppWorld compared to sequential execution.
arXiv:2608. 00881v1 Announce Type: new Abstract: Large language model agents increasingly act through stateful tools, yet model generation and environment execution remain serialized at every step.
By Hao Mark Chen, Jinnan Guo, Wayne Luk, Hongxiang Fan
arXiv:2608.20359v1 Announce Type: new
Abstract: Large language models (LLMs) are deployed for increasingly complex tasks involving planning and multi-step decision making, but high-quality performanc...
By Ravisri Valluri, Tung Nguyen, Aditya Grover
arXiv:2606. 18967v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a representative post-training paradigm for LLMs, enabling strong reasoning and agentic capabilities.
By Minseo Kim, Minjae Lee, Seunghyuk Oh, Kevin Galim, Donghoon Kim, Coleman Hooper, Harman Singh, Amir Gholami, Hyung Il Koo, Wonjun Kang
The paper introduces Speculative Probing, a method that repurposes the speculative‑decoding module of large language models for real‑time classification tasks. By appending a trained soft prompt to the target sequence, the approach leverages the already‑cached KV store during inference, adding negligible overhead while achieving higher accuracy than traditional hidden‑state probes. Experiments on four classification tasks across multiple models show that these lightweight probes outperform zero‑shot GPT‑5.4‑mini and rival or surpass specialized 8B safety classifiers without running a full LLM.
By Collin Zhang, Tingwei Zhang, Vitaly Shmatikov
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
By Dengke Han
arXiv:2607. 25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results.
By Jiabao Ji, Yujian Liu, Li An, Rohit Jain, Gungor Polatkan, Siyu Zhu, Shiyu Chang
arXiv:2608. 01651v1 Announce Type: cross Abstract: Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autoregressive decoding remains memory-bound.
By Li Wang, Yi Su, Xiabao Wu, Chiran You, Yongchao Liu, Zhan Qiu, Juelu Zhang, Jiajun Zheng, Fangxin Liu, Jie Zhang, Chen Tian, Chengying Huan
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.
arXiv:2606. 07846v1 Announce Type: cross Abstract: LLM-agent workflows chain model calls and tool invocations, and spend most of their wall-clock time waiting on upstream operations before downstream ones can start.
By Faisal Fareed
The paper introduces AdaptiveSpec, a training‑free speculative decoding method that simultaneously adapts the per‑step verification rule and the draft‑tree shape using signals generated during decoding. It replaces the fixed token‑match rule with a margin‑based threshold and adjusts tree depth, width, and node count based on draft confidence and recent acceptance history, allowing the total draft count to vary. Experiments on SGLang show up to 56% throughput gains over EAGLE‑3 while maintaining 93% of lossless task accuracy on GSM8K, MATH‑500, and HumanEval across three models.
By Oszk\'ar Urb\'an, Young D. Kwon, Stylianos I. Venieris, Cecilia Mascolo