# Code-Augur: Agentic Vulnerability Detection via Specification Inference

arXiv: https://arxiv.org/abs/2606.18619 · HTML: https://mlsanity.com/paper/2606.18619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 51 references that are in the map.
- First posted on arXiv 17 Jun 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, 17 of 17)

- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [Fuzz4All: Universal Fuzzing with Large Language Models](https://mlsanity.com/paper/2308.04748/) (2023)
- [SpecRover: Code Intent Extraction via LLMs](https://mlsanity.com/paper/2408.02232/) (2024)
- [Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG](https://mlsanity.com/paper/2406.11147/) (2024)
- [Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?](https://mlsanity.com/paper/2310.01831/) (2023)
- [SpecGen: Automated Generation of Formal Program Specifications via Large Language Models](https://mlsanity.com/paper/2401.08807/) (2024)
- [Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives](https://mlsanity.com/paper/2310.01152/) (2023)
- [Prompt Fuzzing for Fuzz Driver Generation](https://mlsanity.com/paper/2312.17677/) (2023)
- [Evaluating LLM-driven User-Intent Formalization for Verification-Aware Languages](https://mlsanity.com/paper/2406.09757/) (2024)
- [Locus: Agentic Predicate Synthesis for Directed Fuzzing](https://mlsanity.com/paper/2508.21302/) (2025)
- [ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System](https://mlsanity.com/paper/2509.14589/) (2025)
- [SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned](https://mlsanity.com/paper/2602.07666/) (2026)
- [VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection](https://mlsanity.com/paper/2509.11523/) (2025)
- [All You Need Is A Fuzzing Brain: An LLM-Powered System for Automated Vulnerability Detection and Patching](https://mlsanity.com/paper/2509.07225/) (2025)
- [FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning](https://mlsanity.com/paper/2604.11556/) (2026)
- [OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security](https://mlsanity.com/paper/2603.08566/) (2026)
- [Agentic Fuzzing: Opportunities and Challenges](https://mlsanity.com/paper/2605.10074/) (2026)

## Abstract (arXiv)

The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained masked for years, surfacing only now with AI agents. Yet the reasoning behind these discoveries remains alarmingly opaque and unvalidated. What assumptions did the agent make about a function's inputs when it deemed that function to be secure? Failures in reasoning and incorrect assumptions can lead to missed vulnerabilities and reduce trust in agentic analysis. We propose a security-specification-first paradigm that (1) exposes the agent's tacit assumptions explicitly as security specifications and (2) continuously refines those specifications via runtime falsification. We realize our approach in Code-Augur, a novel harness for agentic vulnerability detection. Given a codebase, Code-Augur analyzes each component of the system for vulnerable code. When it deems a component to be secure, it commits the local invariants behind that judgment as in-source assertions. In parallel, Code-Augur leverages a guided fuzzer to attempt to falsify those assumptions. When the fuzzer triggers an assertion, this either reveals a genuine vulnerability or a flawed specification to refine. In both cases, this process grounds the agent's understanding, aligning its view of code intent with how the code actually behaves. On real-world subjects, Code-Augur effectively leverages security specifications to detect more vulnerabilities than other state-of-the-art agents. Additionally, Code-Augur found 22 new vulnerabilities in key open-source projects. Compared to curated specialized models like Claude Mythos, Code-Augur offers effective agentic vulnerability detection built on widely available LLMs like Sonnet and DeepSeek.