AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines

arXiv:2610.01108 · cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.CL

Submitted: 2026-10-01

Updated: 2026-10-06

Code: https://github.com/apoorvumang/prompt-lookup-decoding

Terminology

• Verification — 24× in this paper · explained in 2 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Speculative Decoding — 12× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• Generative AI — 3× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 3× in this paper
• Online Adaptation — 3× in this paper · explained in 3 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Multi-Agent System — 2× in this paper · explained in 5 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Accelerating Large Language Model Decoding with Speculative Sampling
• Evaluating Large Language Models Trained on Code
• Gemma 3 Technical Report
• TeamBench: Evaluating Agent Coordination under Enforced Role Separation
• Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
• TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput
• Devstral: Fine-tuning Language Models for Coding Agent Applications
• HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
• CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents

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