# AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration

arXiv: https://arxiv.org/abs/2607.12058 · HTML: https://mlsanity.com/paper/2607.12058/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 10 of 10)

- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [Deep Learning based Vulnerability Detection: Are We There Yet?](https://mlsanity.com/paper/2009.07235/) (2020)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities](https://mlsanity.com/paper/1807.06756/) (2018)
- [RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing](https://mlsanity.com/paper/2501.18160/) (2025)
- [VELVET: a noVel Ensemble Learning approach to automatically locate VulnErable sTatements](https://mlsanity.com/paper/2112.10893/) (2021)
- [On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities](https://mlsanity.com/paper/2401.09767/) (2024)
- [Toward Improved Deep Learning-based Vulnerability Detection](https://mlsanity.com/paper/2403.03024/) (2024)
- [Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Prediction](https://mlsanity.com/paper/2504.13676/) (2025)
- [Utilizing Precise and Complete Code Context to Guide LLM in Automatic False Positive Mitigation](https://mlsanity.com/paper/2411.03079/) (2024)

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

- [Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale](https://mlsanity.com/paper/2609.15939/) (2026)

## Abstract (arXiv)

Given a vulnerability-fixing commit, trigger localization asks which specific statement turns the vulnerable program state into a concrete unsafe operation. This question is harder than binary vulnerability detection because the answer demands interprocedural, causal reasoning: in a substantial fraction of real-world CVEs the triggering statement lies several call layers outside the patched function, beyond the reach of static rule sets and pattern-matching language models alike. We present AutoTrace, an agentic pipeline that localizes vulnerability triggers by exploring a code property graph layer by layer, with LLM agents deciding where to look next and deterministic admissibility gates deciding what evidence is required before a trigger can be reported. Agents never accept a trigger on their own authority; every reported trigger is backed by explicit evidence drawn from the graph, so the pipeline covers both intra- and interprocedural vulnerabilities without relying on ungrounded model judgment. On the full InterPVD benchmark, AutoTrace reaches 75.0% VulnHit and 80.8% FuncHit, surpassing the prior state of the art on the same corpus. Building on the same machinery, we construct SinkTrace-Bench, a dataset that exposes each vulnerability as a source-to-sink (S2S) causal chain from attacker-controlled input through propagation to the dangerous operation, drawn from matched vulnerable and patched program states. It comprises 1,542 verifier-confirmed, perfectly balanced vulnerable/safe samples whose label fidelity we audit against expert annotations. Benchmarking frontier LLMs on it, we find that even the strongest struggle to separate the matched pairs, exposing the causal-reasoning gap that trigger localization targets. Artifact available at https://github.com/Erroristotle/AutoTrace.