Recovering from Misbehaviors in Coding Agents

Rahul Nanda, Chandra Maddila, Smriti Jha, Euna Mehnaz Khan, Satish Chandra, Matteo Paltenghi

Keywords: Artificial Intelligence, Agents, Software Engineering

TL;DR: A self-intervention system to recover from misbehaviors in coding agents at scale

Abstract:

Autonomous coding agents, powered by Large Language Models (LLMs), are increasingly being adopted in the software industry to automate complex engineering tasks. However, these agents are prone to a wide range of misbehaviors, such as deviating from the user's instructions, getting stuck in repetitive loops, or failing to use tools correctly. These failures disrupt the development workflow and often require resource-intensive manual intervention. In this paper, we present a system for automatically recovering from agentic misbehaviors at scale. We first introduce a taxonomy of misbehaviors grounded in an analysis of production traffic, identifying three primary categories: Specification Drift, Reasoning Problems, and Tool Call Failures, which we find occur in about 30% of all agent trajectories.

To address these issues, we developed a lightweight, asynchronous self-intervention system that observes agent trajectories and provides targeted course-correction guidance to nudge the agent back to a productive path. We evaluated our system on over 10,000 real-world agent trajectories and found that it successfully resolves 90% of the misbehaviors that require a single intervention. Furthermore, a live A/B test in our production environment demonstrated that our system leads to a statistically significant reduction in Tool Call Failures, token usage per session and engineer interventions per session. We present our experience designing and deploying this system, offering insights into the challenges of building resilient agentic systems at scale.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public.

Paper Type: Full-length papers (i.e. case studies, theoretical, applied research papers). 8 pages

Reroute: false

Submission Number: 24