Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.33712

Beyond the Prompt: Linking What Developers Ask, Do, and Understand with Coding Agents

Yunhan Qiao·Summit Haque·Christopher Hundhausen
View original source ↗Read source document ↗Export metadata ↓

Abstract

Coding agents can now change code for developers, who describe goals, supply context, and respond to the agent's work. Yet prompts, screen activity, and task success each tell only part of this story. We present Say, Do, Understand, an end-to-end workflow for analyzing what developers write to an agent, what they do while it works, and what they can explain afterwards. The workflow has five stages (Capture, Prepare, Analyze, Integrate, and Interpret) and three instruments: a prompt codebook, a scheme for coding screen-recorded activities and events, and separate rubrics for explaining the process and the solution. We applied it in an observational study of ten experienced developers who used GitHub Copilot on an unfamiliar codebase. Crossing task performance with understanding produced four personas. The two measures agreed for eight developers but split for two: one passed most tests but could not explain the solution, and another passed few tests but explained it well. In this sample, the personas that most often asked the agent to check its work spent the least time testing on their own. These patterns are descriptive and do not generalize beyond the sample. We recommend the workflow to computing educators, industry practitioners, and researchers to adapt and evaluate human--AI communication in software engineering.

Explore related subjects

cs.SE

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Yunhan Qiao, Summit Haque, Christopher Hundhausen. 2026-09-27. Beyond the Prompt: Linking What Developers Ask, Do, and Understand with Coding Agents. https://arxiv.org/abs/2609.33712

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair

Automated program repair has traditionally focused on single-hunk defects, overlooking multi-hunk bugs that are prevalent in real-world systems. Repairing these bugs requires coordinated edits across multiple, disjoint code regions, posing substantially greater challenges. We present the first systematic study of LLM-driven coding agents (Claude Code, Codex, Gemini-cli, and Qwen Code) on this task. We evaluate these four state-of-the-art agents on 404 multi-hunk bugs from the PolyHunk dataset, yielding 1,616 repair trajectories for large-scale behavioral analysis. We employ fine-grained metrics to assess localization, repair accuracy, regression behavior, and operational dynamics across agents. We find that localization capability varies substantially, with Codex achieving the highest success rate (75.3%) and Qwen Code the lowest (40.4%). Repair accuracy also differs widely, ranging from 26.98% (Qwen Code) to 92.82% (Claude Code), and consistently declines with increasing bug dispersion and complexity (hunk divergence and spatial proximity). High-performing agents (Claude Code and Codex) demonstrate superior semantic consistency, achieving positive average regression reduction, whereas lower-performing agents often introduce new test failures. Notably, agents do not fail fast; failed repairs consume substantially more resources (33%-440% more input tokens) and require longer execution time (35%-330%). Additionally, we developed Maple to provide agents with repository-level context. Empirical results show that Maple improves repair accuracy of Gemini-cli by ~21% through enhanced localization. By analyzing fine-grained metrics and trajectory-level analysis, this study moves beyond accuracy to explain how coding agents localize, reason, and act during multi-hunk repair. Our findings underscore the impact of bug divergence and spatial proximity on multi-hunk repair success for coding agents.

cs.SE↗
arXiv2026

Do Newer Models Produce Better Patches? A Non-Functional Quality Study

Repository-level coding benchmarks typically measure progress in model capability by comparing the resolved rates of later and earlier models. However, this focus overlooks whether the non-functional quality of their generated patches has also changed across model generations. This study investigates whether later models produce functionally correct patches with better non-functional characteristics than earlier models on comparable repository-level repair tasks. We conducted two case studies involving four Claude and DeepSeek models on SWE-bench Lite. Using the same SWE-agent functional repair setting, we evaluated the generated patches with CodeQL, CodeScene, CPU time, and peak memory. Our primary analysis compared the models on commonly resolved instances. The static analysis results showed that most CodeQL paired differences were zero and that no CodeQL or CodeScene comparison remained significant after Holm correction. CPU time differences were small and inconsistent across model families, while peak memory usage was slightly higher for the later models under the benchmark test workload, with small absolute differences. Differences in individual CodeQL rules and CodeScene categories varied across model families and did not survive multiple-comparison correction. Overall, later models resolved more instances but showed no consistent improvement in the measured non-functional indicators on tasks solved by both models. Through this study, we hope to encourage a more comprehensive evaluation of models' practical software engineering capabilities.

cs.SE↗
arXiv2026

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing evaluations remain largely result-centric and provide limited insight into hallucination during repair. In APR, hallucination may arise not only in final patches but also in the intermediate artifacts that guide patch generation. To address this gap, we perform a multi-layered analysis of hallucination throughout the APR process. Specifically, we characterize hallucination as the production of patches or intermediate artifacts that are not faithfully grounded in the available repair evidence. We examine repair hallucination in final patches and understanding hallucination in intermediate artifacts through three tasks, namely triggering testcase identification, line coverage prediction, and additional testcase generation. We then evaluate three representative LLMs on 832 Defects4J bugs through automatic evaluation and manual analysis. Our results show that both repair and understanding hallucinations remain prevalent. Across models and settings, only 21.0%-55.9% of generated patches pass the developer-written test suite. Moreover, although more accurate intermediate artifacts are generally associated with successful repairs, this relationship does not always hold. Manual analysis of 812 sampled repairs identifies repair hallucinations in 72.7% of cases, including patches that pass all available tests; incorrect causal localization and incorrect repair strategies account for 45.9% and 18.5% of these hallucinations, respectively. Meanwhile, models frequently misidentify triggering testcases, mispredict line coverage involving branching control flow, and generate additional testcases with missing bug-triggering conditions or incorrect expected behavior.

cs.SE↗