# Cerberus: Multi-Agent Reasoning and Coverage-Guided Exploration for Static Detection of Runtime Errors

arXiv: https://arxiv.org/abs/2512.21431 · HTML: https://mlsanity.com/paper/2512.21431/

## 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 2 of its 24 references that are in the map.
- First posted on arXiv 24 Dec 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 2 of 2)

- [FixEval: Execution-based Evaluation of Program Fixes for Programming Problems](https://mlsanity.com/paper/2206.07796/) (2022)
- [Analyzing and Supporting Adaptation of Online Code Examples](https://mlsanity.com/paper/1905.12111/) (2019)

## Abstract (arXiv)

In several software development scenarios, it is desirable to detect runtime errors and exceptions in code snippets without actual execution. A typical example is to detect runtime exceptions in online code snippets before integrating them into a codebase. In this paper, we propose Cerberus, a novel predictive, execution-free coverage-guided testing framework. Cerberus uses LLMs to generate the inputs that trigger runtime errors and to perform code coverage prediction and error detection without code execution. With a two-phase feedback loop, Cerberus first aims to both increasing code coverage and detecting runtime errors, then shifts to focus only detecting runtime errors when the coverage reaches 100% or its maximum, enabling it to perform better than prompting the LLMs for both purposes. Our empirical evaluation demonstrates that Cerberus performs better than conventional and learning-based testing frameworks for (in)complete code snippets by generating high-coverage test cases more efficiently, leading to the discovery of more runtime errors.