AgentSpec: Speculative Decoding for Batch Inference of LLM Agents

arXiv:2608.24004 · cs.CL · Submitted 2026-08-25 · Read on arXiv

cs.CL

Submitted: 2026-08-25

Updated: 2026-08-25

Comments: EMNLP 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Speculative Decoding — 52× in this paper · explained in 2 episodes
• Redundancy — 33× in this paper · explained in 2 episodes
• Verification — 12× in this paper · explained in 2 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Thinking mode — 6× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 4× in this paper · explained in 3 episodes
• Multi-Token Prediction — 4× in this paper
• Tokenization — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• DeepSeek-V3 Technical Report
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
• TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput
• Large Language Model Agent: A Survey on Methodology, Applications and Challenges
• Autellix: An Efficient Serving Engine for LLM Agents as General Programs
• DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
• SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
• SPIRe: Boosting LLM Inference Throughput with Speculative Decoding
• gpt-oss-120b & gpt-oss-20b Model Card
• Can Language Models Solve Olympiad Programming?
• Efficient Agents: Building Effective Agents While Reducing Cost
• The Internet of Things in the Era of Generative AI: Vision and Challenges
• MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering