# How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions

arXiv: https://arxiv.org/abs/2605.29442 · HTML: https://mlsanity.com/paper/2605.29442/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 53 references that are in the map.
- First posted on arXiv 28 May 2026.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [SWE-chat: Coding Agent Interactions From Real Users in the Wild](https://mlsanity.com/paper/2604.20779/) (2026)
- [Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories](https://mlsanity.com/paper/2511.00197/) (2025)
- [Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows](https://mlsanity.com/paper/2507.08149/) (2025)
- [Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions](https://mlsanity.com/paper/2604.00436/) (2026)
- [Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub](https://mlsanity.com/paper/2601.15195/) (2026)
- [Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity](https://mlsanity.com/paper/2601.18345/) (2026)
- [Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study](https://mlsanity.com/paper/2602.00164/) (2026)
- [NaturalEdit: Code Modification through Direct Interaction with Adaptive Natural Language Representation](https://mlsanity.com/paper/2510.04494/) (2025)
- [ZORO: Active Rules for Reliable Vibe Coding](https://mlsanity.com/paper/2604.15625/) (2026)

## Built on by (most cited first, 14 of 14)

- [Failure as a Process: An Anatomy of CLI Coding Agent Trajectories](https://mlsanity.com/paper/2607.09510/) (2026)
- [Quantifying Overclaiming Propensity in Frontier LLM Agents](https://mlsanity.com/paper/2609.20812/) (2026)
- [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026)
- [Plans They Abandon, Reports They Author: The Narrative Layer of Autonomous Agents](https://mlsanity.com/paper/2609.12205/) (2026)
- [EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments](https://mlsanity.com/paper/2607.02440/) (2026)
- [How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study](https://mlsanity.com/paper/2607.10856/) (2026)
- [From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software](https://mlsanity.com/paper/2607.05677/) (2026)
- [When and How Context Rot Appears in Coding Agents: A White-Box Study of Agent Skills in Code Auditing](https://mlsanity.com/paper/2607.17937/) (2026)
- [Introducing Consort: A Spec-First Agent Framework for Enforced, Test-Driven Development on Live Database Branches](https://mlsanity.com/paper/2609.09671/) (2026)
- [Beyond Token Savings: A Systematic Study of Context Compression in LLM Agents](https://mlsanity.com/paper/2609.32961/) (2026)
- [Opera: A Verbal Critic Framework for Long-horizon Coding Agents](https://mlsanity.com/paper/2609.33987/) (2026)
- [The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow](https://mlsanity.com/paper/2610.17301/) (2026)
- [Measuring and Reducing Unusable Replies of LLM Agents](https://mlsanity.com/paper/2610.19659/) (2026)
- [What Coding Agents Leave Unsaid: Measuring Task-State Gaps Between Execution and Reports](https://mlsanity.com/paper/2610.20003/) (2026)

## Abstract (arXiv)

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of 20,574 coding-agent sessions from 1,639 repositories across IDE and CLI workflows. We operationalize misalignment as a breakdown made visible through developer pushback, and annotate each episode along four axes: form, cause, cost, and resolution. We identify seven recurring forms, spanning how agents read projects, interpret developer intent, follow rules, bound their actions, implement and execute code, and report progress. 90.50% of episodes impose effort and trust costs rather than irreversible system damage, yet 91.49% of visible resolutions still require explicit user correction. Misalignment patterns also differ across IDE and CLI settings, persist across adjacent sessions, and shift over time: while overall rates decline, constraint violations and inaccurate self-reporting grow in share. Our findings inform the design of training, evaluation, and interfaces for keeping coding agents aligned with real developer workflows.