# Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries

arXiv: https://arxiv.org/abs/2605.15097 · HTML: https://mlsanity.com/paper/2605.15097/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 62 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 16 of 16)

- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks](https://mlsanity.com/paper/2506.11791/) (2025)
- [EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities](https://mlsanity.com/paper/2409.16165/) (2024)
- [RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing](https://mlsanity.com/paper/2501.18160/) (2025)
- [Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs](https://mlsanity.com/paper/2502.19411/) (2025)
- [Reasoning Runtime Behavior of a Program with LLM: How Far Are We?](https://mlsanity.com/paper/2403.16437/) (2024)
- [To Err is Machine: Vulnerability Detection Challenges LLM Reasoning](https://mlsanity.com/paper/2403.17218/) (2024)
- [CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution](https://mlsanity.com/paper/2505.17107/) (2025)
- [Harnessing the Power of LLM to Support Binary Taint Analysis](https://mlsanity.com/paper/2310.08275/) (2023)
- [VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection](https://mlsanity.com/paper/2512.07533/) (2025)
- [Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data](https://mlsanity.com/paper/2506.07390/) (2025)
- [BugScope: Learn to Find Bugs Like Human](https://mlsanity.com/paper/2507.15671/) (2025)
- [VulBinLLM: LLM-powered Vulnerability Detection for Stripped Binaries](https://mlsanity.com/paper/2505.22010/) (2025)
- [LLM-based Vulnerability Discovery through the Lens of Code Metrics](https://mlsanity.com/paper/2509.19117/) (2025)
- [ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software](https://mlsanity.com/paper/2408.02153/) (2024)

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

- [Malaika: Understanding Malware through Tri-Grounded Agentic Reasoning](https://mlsanity.com/paper/2607.09179/) (2026)

## Abstract (arXiv)

Frontier LLM agents are increasingly capable of localizing suspicious code, but vulnerability reasoning requires more than access to program artifacts. An agent must carry forward the evidence that actually decides whether a vulnerability exists. Otherwise, safety-relevant facts may be present in the artifact but absent from the reasoning used to justify the claim, creating a semantic gap between available program facts and the evidence used by the agent. This problem is especially acute for stripped binaries, where source-level cues are removed and relevant evidence is fragmented across noisy lifted IR and lossy decompiled views. We formulate stripped-binary vulnerability reasoning as a semantic grounding problem and present Veritas, a three-stage framework for reliable analysis. First, a static-analysis Slicer recovers witness-backed source-to-sink flows from lifted LLVM IR. Second, an LLM-based Discover stage aligns decompiled code with IR witnesses to construct vulnerability claims. Third, a multi-agent Validator checks these claims through guided debugging and runtime oracles. Together, these stages turn fragmented binary views into checkable claims rather than relying on direct agent inference. We instantiate Veritas for out-of-bounds vulnerabilities and evaluate it on a curated benchmark with flow-level annotations. Veritas achieves 90% recall, outperforms static, dynamic, binary-analysis, and agentic baselines, and reports no false positives among 623 exhaustively validated candidates and only two observed false positives in sampled audits. In a real-world case study, Veritas discovered a previously unknown Apple vulnerability that was confirmed and assigned a CVE, demonstrating that grounded reasoning can produce actionable findings beyond the curated benchmark.