# Deep Agentic Search for Repository-Level Code Question Answering: An Empirical Study

arXiv: https://arxiv.org/abs/2608.01507 · HTML: https://mlsanity.com/paper/2608.01507/

## Key facts

- Cited by 1 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 41 of its 58 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Placed in

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

## Builds on (most cited first, 30 of 41)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [DeepAgent: A General Reasoning Agent with Scalable Toolsets](https://mlsanity.com/paper/2510.21618/) (2025)
- [CoIR: A Comprehensive Benchmark for Code Information Retrieval Models](https://mlsanity.com/paper/2407.02883/) (2024)
- [Chain-of-Retrieval Augmented Generation](https://mlsanity.com/paper/2501.14342/) (2025)
- [The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents](https://mlsanity.com/paper/2511.03690/) (2025)
- [SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents](https://mlsanity.com/paper/2601.16746/) (2026)
- [LongCodeZip: Compress Long Context for Code Language Models](https://mlsanity.com/paper/2510.00446/) (2025)
- [SWE-QA: Can Language Models Answer Repository-level Code Questions?](https://mlsanity.com/paper/2509.14635/) (2025)
- [Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems](https://mlsanity.com/paper/2604.14228/) (2026)
- [LongCodeBench: Evaluating Coding LLMs at 1M Context Windows](https://mlsanity.com/paper/2505.07897/) (2025)
- [Is Grep All You Need? How Agent Harnesses Reshape Agentic Search](https://mlsanity.com/paper/2605.15184/) (2026)
- [SWE-Explore: Benchmarking How Coding Agents Explore Repositories](https://mlsanity.com/paper/2606.07297/) (2026)
- [CoReQA: Uncovering Potentials of Language Models in Code Repository Question Answering](https://mlsanity.com/paper/2501.03447/) (2025)
- [Decoding the Configuration of AI Coding Agents: Insights from Claude Code Projects](https://mlsanity.com/paper/2511.09268/) (2025)
- [Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding](https://mlsanity.com/paper/2602.01785/) (2026)
- [CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents](https://mlsanity.com/paper/2406.11589/) (2024)
- [CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering](https://mlsanity.com/paper/2412.14764/) (2024)
- [SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding](https://mlsanity.com/paper/2603.16124/) (2026)
- [RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval](https://mlsanity.com/paper/2509.25257/) (2025)
- [Leveraging Large Language Models in Code Question Answering: Baselines and Issues](https://mlsanity.com/paper/2411.03012/) (2024)
- [SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution](https://mlsanity.com/paper/2605.08366/) (2026)
- [FastContext: Training Efficient Repository Explorer for Coding Agents](https://mlsanity.com/paper/2606.14066/) (2026)
- [Agentic Code Reasoning](https://mlsanity.com/paper/2603.01896/) (2026)
- [CodeSimpleQA: Scaling Factuality in Code Large Language Models](https://mlsanity.com/paper/2512.19424/) (2025)
- [RubberDuckBench: A Benchmark for AI Coding Assistants](https://mlsanity.com/paper/2601.16456/) (2026)
- [Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering](https://mlsanity.com/paper/2603.26567/) (2026)
- [RefactorCoderQA: Benchmarking LLMs for Multi-Domain Coding Question Solutions in Cloud and Edge Deployment](https://mlsanity.com/paper/2509.10436/) (2025)
- [SimpleDevQA: Benchmarking Large Language Models on Development Knowledge QA](https://mlsanity.com/paper/2512.08867/) (2025)
- [LogicLens: Leveraging Semantic Code Graph to explore Multi Repository large systems](https://mlsanity.com/paper/2601.10773/) (2026)

## Built on by (most cited first, 1 of 1)

- [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026)

## Abstract (arXiv)

Code agents spend much of their effort simply locating the right code inside a repository. Two approaches dominate current practice. In Semantic Search, the agent retrieves code blocks from a vector index built from the repository in advance. In Deep Agentic Search (also known as grep-search by subagent), a planning agent delegates the exploration to a separate subagent that works in an isolated context window and returns only a condensed result. The second design, which is considered good context engineering practice, exists to protect the main agent from context pollution (also known as context rot), the loss of accuracy that occurs as unrelated material accumulates in the context window. Recent code agents (such as Claude Code, Codex, Antigravity, etc) have adopted it quickly, but there is little evidence on whether it produces better answers. We compare the two approaches on SWE-QA, a benchmark for repository-level code question answering. Semantic search answered 65.2% of questions correctly against 46.2% for deep agentic search, and it produced each correct answer at less than half the cost. To explain the gap, we then coded every failed run into a taxonomy of failure modes. The taxonomy shows that deep agentic search did not remove failures but introduced a new class of them: the single largest share of its failures, 41.8%, occurred at the hand-off between the planner and its sub-agent, and these were usually silent, ending in a fluent and confident answer that was wrong. Deep agentic search addresses a real problem and is now the preferred design in many code agents. However, our results show that the protection it offers may not be free, and that for read-only questions over a repository that can be indexed, retrieval was the stronger and cheaper option.