Debugging Researchers find AI is pretty bad at debugging—but they’re working on it Even when given access to tools, AI agents can't reliably debug software. Samuel Axon – Apr 11, 2025 6:26 pm | 0 Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only   Learn more There are few areas where AI has seen more robust deployment than the field of software development. From "vibe" coding to GitHub Copilot to startups building quick-and-dirty applications with support from LLMs, AI is already deeply integrated. However, those claiming we're mere months away from AI agents replacing most programmers should adjust their expectations because models aren't good enough at the debugging part, and debugging occupies most of a developer's time. That's the suggestion of Microsoft Research, which built a new tool called debug-gym to test and improve how AI models can debug software. Debug-gym (available on GitHub and detailed in a blog post) is an environment that allows AI models to try and debug any existing code repository with access to debugging tools that aren't historically part of the process for these models. Microsoft found that without this approach, models are quite notably bad at debugging tasks. With the approach, they're better but still a far cry from what an experienced human developer can do. Here's how Microsoft's researchers describe debug-gym: Debug-gym expands an agent’s action and observation space with feedback from tool usage, enabling setting breakpoints, navigating code, printing variable values, and creating test functions. Agents can interact with tools to investigate code or rewrite it, if confident. We believe interactive debugging with proper tools can empower coding agents to tackle real-world software engineering tasks and is central to LLM-based agent research. The fixes proposed by a coding agent with debugging capabilities, and then approved by a human programmer, will be grounded in the context of the relevant codebase, program execution and documentation, rather than relying solely on guesses based on previously seen training data. Pictured below are the results of the tests using debug-gym. Agents using debugging tools drastically outperformed those that didn't, but their success rate still wasn't high enough. Credit: Microsoft Research This approach is much more successful than relying on the models as they're usually used, but when your best case is a 48.4 percent success rate, you're not ready for primetime. The limitations are likely because the models don't fully understand how to best use the tools, and because their current training data is not tailored to this use case. "We believe this is due to the scarcity of data representing sequential decision-making behavior (e.g., debugging traces) in the current LLM training corpus," the blog post says. "However, the significant performance improvement... validates that this is a promising research direction." This initial report is just the start of the efforts, the post claims.  The next step is to "fine-tune an info-seeking model specialized in gathering the necessary information to resolve bugs." If the model is large, the best move to save inference costs may be to "build a smaller info-seeking model that can provide relevant information to the larger one." This isn't the first time we've seen outcomes that suggest some of the ambitious ideas about AI agents directly replacing developers are pretty far from reality. There have been numerous studies already showing that even though an AI tool can sometimes create an application that seems acceptable to the user for a narrow task, the models tend to produce code laden with bugs and security vulnerabilities, and they aren't generally capable of fixing those problems. This is an early step on the path to AI coding agents, but most researchers agree it remains likely that the best outcome is an agent that saves a human developer a substantial amount of time, not one that can do everything they can do. Samuel Axon Senior Editor Samuel Axon Senior Editor Samuel Axon is a senior editor at Ars Technica, where he is the editorial director for tech and gaming coverage. He covers AI, software development, gaming, entertainment, and mixed reality. He has been writing about gaming and technology for nearly two decades at Engadget, PC World, Mashable, Vice, Polygon, Wired, and others. He previously ran a marketing and PR agency in the gaming industry, led editorial for the TV network CBS, and worked on social media marketing strategy for Samsung Mobile at the creative agency SPCSHP. He also is an independent software and game developer for iOS, Windows, and other platforms, and he is a graduate of DePaul University, where he studied interactive media and software development. 0 Comments