# DepRadar: Agentic Coordination for Context Aware Defect Impact Analysis in Deep Learning Libraries

arXiv: https://arxiv.org/abs/2601.09440 · HTML: https://mlsanity.com/paper/2601.09440/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 14 Jan 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, 18 of 18)

- [Toward Understanding Deep Learning Framework Bugs](https://mlsanity.com/paper/2203.04026/) (2022)
- [Do Developers Update Their Library Dependencies? An Empirical Study on the Impact of Security Advisories on Library Migration](https://mlsanity.com/paper/1709.04621/) (2017)
- [An Empirical Comparison of Dependency Network Evolution in Seven Software Packaging Ecosystems](https://mlsanity.com/paper/1710.04936/) (2017)
- [PyCG: Practical Call Graph Generation in Python](https://mlsanity.com/paper/2103.00587/) (2021)
- [A Fine-grained Data Set and Analysis of Tangling in Bug Fixing Commits](https://mlsanity.com/paper/2011.06244/) (2020)
- [Untangling Fine-Grained Code Changes](https://mlsanity.com/paper/1502.06757/) (2015)
- [Bug Characterization in Machine Learning-based Systems](https://mlsanity.com/paper/2307.14512/) (2023)
- [Generative AI for Pull Request Descriptions: Adoption, Impact, and Developer Interventions](https://mlsanity.com/paper/2402.08967/) (2024)
- [Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks](https://mlsanity.com/paper/2506.14813/) (2025)
- [Demystifying the Vulnerability Propagation and Its Evolution via Dependency Trees in the NPM Ecosystem](https://mlsanity.com/paper/2201.03981/) (2022)
- [CHRONOS: Time-Aware Zero-Shot Identification of Libraries from Vulnerability Reports](https://mlsanity.com/paper/2301.03944/) (2023)
- [Mitigating Persistence of Open-Source Vulnerabilities in Maven Ecosystem](https://mlsanity.com/paper/2308.03419/) (2023)
- [Exploiting Library Vulnerability via Migration Based Automating Test Generation](https://mlsanity.com/paper/2312.09564/) (2023)
- [An Empirical Study of Vulnerable Package Dependencies in LLM Repositories](https://mlsanity.com/paper/2508.21417/) (2025)
- [Compatible Remediation on Vulnerabilities from Third-Party Libraries for Java Projects](https://mlsanity.com/paper/2301.08434/) (2023)
- [Ecosystem-wide influences on pull request decisions: insights from NPM](https://mlsanity.com/paper/2410.14695/) (2024)
- [A Survey of Third-Party Library Security Research in Application Software](https://mlsanity.com/paper/2404.17955/) (2024)
- [Does the Vulnerability Threaten Our Projects? Automated Vulnerable API Detection for Third-Party Libraries](https://mlsanity.com/paper/2409.02753/) (2024)

## Abstract (arXiv)

Deep learning libraries like Transformers and Megatron are now widely adopted in modern AI programs. However, when these libraries introduce defects, ranging from silent computation errors to subtle performance regressions, it is often challenging for downstream users to assess whether their own programs are affected. Such impact analysis requires not only understanding the defect semantics but also checking whether the client code satisfies complex triggering conditions involving configuration flags, runtime environments, and indirect API usage. We present DepRadar, an agent coordination framework for fine grained defect and impact analysis in DL library updates. DepRadar coordinates four specialized agents across three steps: 1. the PR Miner and Code Diff Analyzer extract structured defect semantics from commits or pull requests, 2. the Orchestrator Agent synthesizes these signals into a unified defect pattern with trigger conditions, and 3. the Impact Analyzer checks downstream programs to determine whether the defect can be triggered. To improve accuracy and explainability, DepRadar integrates static analysis with DL-specific domain rules for defect reasoning and client side tracing. We evaluate DepRadar on 157 PRs and 70 commits across two representative DL libraries. It achieves 90% precision in defect identification and generates high quality structured fields (average field score 1.6). On 122 client programs, DepRadar identifies affected cases with 90% recall and 80% precision, substantially outperforming other baselines.