AgentArmor: A Framework, Evaluation, \& Mitigation of Coding Agent Failures

2026-06-13

AI Summary

This work systematically investigates the root causes of rare yet potentially severe failures in deployed AI coding agents, attributing them to three primary mechanisms: underspecification, capability gaps, and execution errors. To address these issues, the authors introduce AgentArmor, a comprehensive safety framework integrating an expanded system prompt, a standalone command classifier, a “three-strikes” policy, deterministic guardrails, and a context-aware self-editing tool. They also establish a rigorous evaluation suite comprising eight assessment dimensions, twenty coding environments, and fifty-nine synthetic dialogue templates. Experimental results demonstrate that AgentArmor significantly enhances the safety of coding agents on statistically significant samples, offering a practical and deployable mitigation strategy for current and future agent systems.

Abstract

Software engineering and deployment are increasingly being delegated to AI coding agents. The scale of their adoption is surfacing rare, but highly destructive, failure modes. In this paper, we study these failure modes as stemming from three distinct mechanisms: underspecification, where default model behavior is unsafe; capability errors, where the safe action is available but the model does not adhere to it due to bias or capability limitations; and agent harness errors, where the model fails to execute the safe action through the harness. We evaluate these across 8 different evaluations, each inspired by real-life deployment failures, totaling 20 coding environments and 59 synthetic transcript templates. Based on this evaluation, we propose AgentArmor, an agent harness modification, to mitigate these errors. By adding an extended system prompt, a separate command classifier, a ``3 strikes'' policy, deterministic guardrails, and tools for the agent to edit its own context, we show that AgentArmor is safer across a statistically significant number of samples. Thus, we suggest concrete mitigations for current coding agents and a design philosophy for future agent harness features.

Problem

• AI coding agents
• failure modes
• underspecification
• capability errors
• agent harness errors

Innovation

• AgentArmor
• coding agent failures
• agent harness
• safety mitigation
• system prompt