# WatchPoint: Executable User Feedback for Real-World Agentic Web Development

arXiv: https://arxiv.org/abs/2609.26204 · HTML: https://mlsanity.com/paper/2609.26204/

## 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 22 of its 25 references that are in the map.
- First posted on arXiv 10 Aug 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, 22 of 22)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions](https://mlsanity.com/paper/2409.16427/) (2024)
- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation](https://mlsanity.com/paper/2507.04952/) (2025)
- [Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks](https://mlsanity.com/paper/2505.07473/) (2025)
- [Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations](https://mlsanity.com/paper/2601.17087/) (2026)
- [When Agents go Astray: Course-Correcting SWE Agents with PRMs](https://mlsanity.com/paper/2509.02360/) (2025)
- [SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories](https://mlsanity.com/paper/2512.17419/) (2025)
- [WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning](https://mlsanity.com/paper/2509.22644/) (2025)
- [ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding](https://mlsanity.com/paper/2510.11498/) (2025)
- [FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback](https://mlsanity.com/paper/2601.04203/) (2025)
- [FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks](https://mlsanity.com/paper/2504.06939/) (2025)
- [InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration](https://mlsanity.com/paper/2510.18327/) (2025)

## Abstract (arXiv)

When a professional web developer's code fails a test, they do not simply re-read the stack trace. They open the application in a browser, click buttons, inspect computed styles, and run diagnostic commands to understand what went wrong. Existing feedback mechanisms for coding agents rely on screenshots, LLM-as-a-judge scoring, or natural-language corrections, but few interact with the live application the way a developer would. We introduce WatchPoint, a simulated-user system that mimics real developer behavior by generating and executing diagnostic scripts against the running application, producing structured observations that guide the coding model's retry. Unlike prior approaches that target single-file edits or evaluate using non-executable metrics, we operate on Web-Bench, a benchmark of 50 multi-file web projects comprising 1,000 sequentially dependent tasks, verified by deterministic end-to-end tests. WatchPoint recovers 57.6% of the tasks it diagnoses, and a controlled user study confirms the simulation's realism: human testers achieve a comparable recovery rate (54.5%), providing evidence that automated diagnostic scripts can substitute for interactive human testing on sequential web development tasks. We further identify a pattern of capability gaps that governs when simulated-user feedback is helpful and when it should be withheld.