# SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion

arXiv: https://arxiv.org/abs/2510.17925 · HTML: https://mlsanity.com/paper/2510.17925/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 23 of 23)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [The Stack: 3 TB of permissively licensed source code](https://mlsanity.com/paper/2211.15533/) (2022)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph](https://mlsanity.com/paper/2410.14684/) (2024)
- [The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason](https://mlsanity.com/paper/2506.12286/) (2025)
- [Language Models for Code Completion: A Practical Evaluation](https://mlsanity.com/paper/2402.16197/) (2024)
- [REPOFUSE: Repository-Level Code Completion with Fused Dual Context](https://mlsanity.com/paper/2402.14323/) (2024)
- [HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation](https://mlsanity.com/paper/2406.06918/) (2024)
- [Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review](https://mlsanity.com/paper/2406.12655/) (2024)
- [Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs](https://mlsanity.com/paper/2406.18294/) (2024)
- [Accelerating Code Search with Deep Hashing and Code Classification](https://mlsanity.com/paper/2203.15287/) (2022)
- [Leveraging Large Language Models for Code Translation and Software Development in Scientific Computing](https://mlsanity.com/paper/2410.24119/) (2024)
- [SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval](https://mlsanity.com/paper/2508.00546/) (2025)
- [SECRET: Towards Scalable and Efficient Code Retrieval via Segmented Deep Hashing](https://mlsanity.com/paper/2412.11728/) (2024)

## Built on by (most cited first, 3 of 3)

- [Contract-Coding: Towards Repo-Level Generation via Structured Symbolic Paradigm](https://mlsanity.com/paper/2604.13100/) (2026)
- [ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation](https://mlsanity.com/paper/2607.08691/) (2026)
- [CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents](https://mlsanity.com/paper/2607.25431/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting repository context at inference time. The low inference-time latency budget affects either retrieval quality or the added latency adversely impacts user experience. We address this limitation with SpecAgent, an agent that improves both latency and code-generation quality by proactively exploring repository files during indexing and constructing speculative context that anticipates future edits in each file. This indexing-time asynchrony allows thorough context computation, masking latency, and the speculative nature of the context improves code-generation quality. Additionally, we identify the problem of future context leakage in existing benchmarks, which can inflate reported performance. To address this, we construct a synthetic, leakage-free benchmark that enables a more realistic evaluation of our agent against baselines. Experiments show that SpecAgent consistently achieves absolute gains of 9-11% (48-58% relative) compared to the best-performing baselines, while significantly reducing inference latency.