DeepRepoQA is proposed, a novel question answering (QA) framework for repository-level code understanding that builds on an agentic framework where LLM agents find answers through a systematic tree search over the repository structure.
Abstract
Answering developer questions about a software repository is a critical yet under-explored problem in software engineering. While existing repository understanding methods have advanced the field, they predominantly rely on surface-level code retrieval and lack the ability for deep reasoning over multiple files, complex software architectures, and grounding answers in long-range code dependencies. To address these limitations, we propose DeepRepoQA, a novel question answering (QA) framework for repository-level code understanding. DeepRepoQA builds on an agentic framework where LLM agents find answers through a systematic tree search over the repository structure. A Monte-Carlo Tree Search (MCTS) mechanism is employed to empower agents to dynamically search, navigate, and inspect code, enabling effective multi-hop reasoning over long-range code dependencies. Comprehensive experiments on the SWE-QA benchmark demonstrate substantial performance gains over strong baselines, validating the effectiveness of systematic MCTS-guided exploration for multi-hop repository reasoning.
The results show that the protection deep agentic search 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.
Amirkia Rafiei Oskooei, Bora Ilci, Alperen Kayim et al.· 0 citations
This work introduces a verifiable benchmark of 500 deep research tasks spanning 31 topics and 10 major categories, with three query forms designed to probe complementary capabilities required for deep research.
Can Wang, Hao-Ran Chen, Hao Gao et al.· 0 citations
This work presents SciDataSailor, a framework for synthesizing tool-interactive trajectories by balancing broad exploration with targeted exploitation and presents SciDataSailor, a framework for synthesizing tool-interactive trajectories as Monte Carlo Tree Search (MCTS) with four task-specific mechanisms.
J. Rao, Yicheng Qiu, Chi Zhang et al.· arXiv.org· 1 citation
This paper proposes DocTrace, a hierarchical framework that progressively performs evidence localization, structured document parsing, and evidence graph reasoning to enable explicit evidence provenance, and develops a two-stage training framework.
Lei Xiang, Zhi-Cheng Guan, Hong Chen et al.· 0 citations
Large language model (LLM)-powered coding agents have made rapid progress in automating software engineering tasks, yet repository-level issue resolution remains challenging. Beyond generating a plausible patch, an agent must localize relevant code across interdependent files and maintain repository context that is both sufficient and focused. Code graphs expose non-local relations, but linear text interfaces obscure their topology; rendering the full repository graph yields visual representations that are too dense to perceive reliably, whereas a one-shot local view becomes stale as exploration proceeds. We present \textbf{RepoAtlas}, a training-free module that maintains evolving multimodal repository views through a \emph{select--project--refresh} loop over a repository code graph. RepoAtlas combines evidence from the issue with the agent's current exploration state to select a task-relevant region under a fixed budget, projects the selected structure into complementary visual and textual representations, and refreshes the view when changes in the exploration state render it outdated. We evaluate RepoAtlas on SWE-bench Verified, where it improves the resolve rate by 2.4 points while reducing input tokens and model calls by 5.8\% and 7.8\% on average, relative to the strongest multimodal graph baseline, with consistent gains across three models of different families and scales.
Yun-Xiang Zhang, Hai-Quan Wang, Jia-Wei Guo et al.· 0 citations
Experiments establish ReTree as an effective self-correcting memory abstraction for long-horizon search, and show that ReTree consistently outperforms Full-Trajectory ReAct in question-answering and search benchmarks.
Aijun Yang, Qianxue Guo, Ziyi Huang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
