paper-with-me

Papers

Speculative Actions: A Lossless Framework for Faster Agentic Systems

2025-10-05 · Naimeng Ye, Arnav Ahuja, Georgios Liargkovas, Yunan Lu, Kostis Kaffes, Tianyi Peng arxiv

AI agents are increasingly deployed in complex, interactive environments, yet their runtime remains a major bottleneck for training, evaluation, and real-world use. Typical agent behavior unfolds sequentially, with each action requiring an API call that can incur substantial latency. For example, a game of chess between two state-of-the-art agents can take hours. We introduce Speculative Actions, a lossless acceleration framework for general agentic systems. Inspired by speculative execution in microprocessors and speculative decoding in LLM inference, our method uses faster models to predict likely future actions and execute them in parallel, committing only when predictions match. We evaluate speculative actions across gaming, e-commerce, and web search environments, and additionally study a lossy extension in an operating systems setting. Across domains, we achieve up to 55% next-action prediction accuracy, translating into up to 20% latency reductions. Finally, we present a cost-latency analysis that formalizes the tradeoff between speculative breadth and time savings. This analysis enables principled tuning and selective branch launching to ensure that multi-branch speculation delivers practical speedups without prohibitive cost growth.

📄 PDF Abstract BibTeX arXiv:2510.04371

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs

2026-08-26 · Sheng Liang, Yongyue Zhang, Nathanael Brian, Hang Lv 외 arxiv

Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions. To control latency, deployments routinely compress inputs, but this degrades task accu…

A Practical Investigation of Training-free Relaxed Speculative Decoding

2026-07-09 · Guoxuan Xia, Luka Ribar, Paul Balanca arxiv

Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its reject…

Dynamic Speculative Agent Planning

2025-09-02 · Yilin Guan, Qingfeng Lan, Sun Fei, Dujian Ding 외 arxiv

Despite their remarkable success in complex tasks propelling widespread adoption, large language-model-based agents still face critical deployment challenges due to prohibitive latency and inference costs. While recent w…

Reinforcement Learning

Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding

2025-09-15 · Mingxiao Huo, Jiayi Zhang, Hewei Wang, Jinfeng Xu 외 arxiv

Vision-Language Models (VLMs) enable powerful multimodal reasoning but suffer from slow autoregressive inference, limiting their deployment in real-time applications. We introduce Spec-LLaVA, a system that applies specul…

Multimodal Reasoning

Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference

2024-05-23 · Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky 외

This paper introduces distributed speculative inference (DSI), a novel inference algorithm that is provably faster than speculative inference (SI) [leviathan2023, chen2023, miao2024, sun2025, timor2025] and standard auto…

Language ModelingLanguage Modelling