Papers with Low inference time latency
SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion (2026.acl-long)
Copied to clipboard
George Ma, Anurag Koul, Qi Chen, Yawen Wu, Sachit Kuhar, Yu Yu, Aritra Sengupta, Varun Kumar, Murali Krishna Ramanathan
| Challenge: | Large Language Models (LLMs) excel at code-related tasks but struggle in real software repositories. |
| Approach: | They propose a large-scale agent that injects repository context at inference time to improve both latency and code-generation quality by proactively exploring repository files during indexing and constructing speculative context. |
| Outcome: | Experiments show that SpecAgent achieves 9–11% relative performance gains compared to baselines while significantly reducing inference latency. |