English
Related papers

Related papers: B-PASTE: Beam-Aware Pattern-Guided Speculative Exe…

200 papers

Speculative decoding accelerates LLM inference by letting a small drafter propose multiple tokens which a large target model verifies once per speculation step. As vocabularies scale past 10e5 tokens,verification cost in the target model is…

Computation and Language · Computer Science 2026-02-04 Jinbin Zhang , Nasib Ullah , Erik Schultheis , Rohit Babbar

We present Speculative Rollout with Tree-Structured Cache (SRT), a simple, model-free approach to accelerate on-policy reinforcement learning (RL) for language models without sacrificing distributional correctness. SRT exploits the…

Machine Learning · Computer Science 2026-01-15 Chi-Chih Chang , Siqi Zhu , Zhichen Zeng , Haibin Lin , Jiaxuan You , Mohamed S. Abdelfattah , Ziheng Jiang , Xuehai Qian

With the rapid advancement of artificial intelligence, there is an increasing demand for intelligent robots capable of assisting humans in daily tasks and performing complex operations. Such robots not only require task planning…

Robotics · Computer Science 2025-05-01 Huihui Guo , Huilong Pi , Yunchuan Qin , Zhuo Tang , Kenli Li

Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In…

Autoregressive decoding makes the inference of Large Language Models (LLMs) time-consuming. In this paper, we reconsider speculative sampling and derive two key observations. Firstly, autoregression at the feature (second-to-top-layer)…

Machine Learning · Computer Science 2025-03-05 Yuhui Li , Fangyun Wei , Chao Zhang , Hongyang Zhang

Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inference latency. This bottleneck has emerged as a central obstacle…

Computation and Language · Computer Science 2025-09-30 Maxim Divilkovskiy , Vitaly Malygin , Sergey Zlobin , Stanislav Ilyushin , Sultan Isali , Vasily Kalugin , Nuriza Aitassova , Fei Yi , Weidi Zeng

LLM agents that operate over long context depend on external memory to accumulate knowledge over time. However, existing methods typically store each observation as a single deterministic conclusion (e.g., inferring "API~X failed" from…

Artificial Intelligence · Computer Science 2026-05-11 Junfeng Liao , Qizhou Wang , Jianing Zhu , Bo Du , Rui Yan , Xiuying Chen

Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated. LLMs enable a new type of workload, agentic pipeline search, in which autonomous or semi-autonomous agents generate,…

Databases · Computer Science 2026-03-06 Arnab Phani , Elias Strauss , Sebastian Schelter

LLM inference on mobile devices faces extraneous challenges due to limited memory bandwidth and computational resources. To address these issues, speculative inference and processing-in-memory (PIM) techniques have been explored at the…

Hardware Architecture · Computer Science 2025-09-03 Siyuan He , Zhantong Zhu , Yandong He , Tianyu Jia

We present the design and implementation of a tool called TASE that uses transactional memory to reduce the latency of symbolic-execution applications with small amounts of symbolic state. Execution paths are executed natively while…

Cryptography and Security · Computer Science 2020-01-01 Adam Humphries , Kartik Cating-Subramanian , Michael K. Reiter

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Machine Learning · Computer Science 2026-01-07 Tuc Nguyen , Thai Le

Symbolic execution is a widely used technique for test generation, offering systematic exploration of program paths through constraint solving. However, it is fundamentally constrained by the capability to model the target code, including…

Software Engineering · Computer Science 2026-02-12 Yaoxuan Wu , Xiaojie Zhou , Ahmad Humayun , Muhammad Ali Gulzar , Miryung Kim

Natural Language Processing (NLP) inference is seeing increasing adoption by mobile applications, where on-device inference is desirable for crucially preserving user data privacy and avoiding network roundtrips. Yet, the unprecedented size…

Machine Learning · Computer Science 2023-02-01 Liwei Guo , Wonkyo Choe , Felix Xiaozhu Lin

Large Language Models can break through knowledge and timeliness limitations by invoking external tools within the Model Context Protocol framework to achieve automated execution of complex tasks. However, with the rapid growth of…

Software Engineering · Computer Science 2025-11-26 Qingsong He , Jing Nan , Jiayu Jiao , Liangjie Tang , Xiaodong Xu , Mengmeng Sun , Qingyao Wang , Minghui Yan

Sequential reasoning in agent systems has been significantly advanced by large language models (LLMs), yet existing approaches face limitations. Reflection-driven reasoning relies solely on knowledge in pretrained models, limiting…

Machine Learning · Computer Science 2024-10-23 Chen Yang , Chenyang Zhao , Quanquan Gu , Dongruo Zhou

In human-written articles, we often leverage the subtleties of text style, such as bold and italics, to guide the attention of readers. These textual emphases are vital for the readers to grasp the conveyed information. When interacting…

Computation and Language · Computer Science 2024-10-02 Qingru Zhang , Chandan Singh , Liyuan Liu , Xiaodong Liu , Bin Yu , Jianfeng Gao , Tuo Zhao

LLM-agent simulation offers a flexible computational tool for studying population response trajectories that depend on scenario events, memory, demographics, and evolving social context. However, full multi-round simulation scales linearly…

Multiagent Systems · Computer Science 2026-05-28 Quan Zheng , Yan Gao , Shaobin He , Haoxiang Guan , Yuanhe Tian , Jie Feng , Ming Wang , Shuxin Zheng , Zhen Liu

Scaling test-time computation improves performance across different tasks on large language models (LLMs), which has also been extended to tool-augmented agents. For these agents, scaling involves not only "thinking" in tokens but also…

Tool-augmented LLMs are increasingly deployed as agents that interleave natural-language reasoning with executable Python actions, as in CodeAct-style frameworks. In deployment, these agents rely on runtime state that persists across steps.…

Artificial Intelligence · Computer Science 2026-03-06 Victor May , Aaditya Salgarkar , Yishan Wang , Diganta Misra , Huu Nguyen

Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks. With only a few demonstration examples, these LLMs can quickly adapt to target tasks without expensive gradient updates. Common…

Computation and Language · Computer Science 2023-11-14 Yue Yu , Jiaming Shen , Tianqi Liu , Zhen Qin , Jing Nathan Yan , Jialu Liu , Chao Zhang , Michael Bendersky