Enforcing Code Reasoning in Agentic Scaffold for More Effective Issue Resolution
[Inżynieria oprogramowania] Autorzy: Changshu Liu, Ji young Kim, Alireza Ghazanfari i 2 więcej
Reasoning is central to ReAct-based programming agents, yet whether and how they reason about code remains unclear. We study 7,955 issue-resolution trajectories from six single- and multi-agent scaffolds across four programming languages on SWE-bench-Verified, SWE-bench-Pro, and SWE-bench-Lite. We identify 12 forms of code reasoning in 66.95% of trajectories. Code reasoning is associated with higher resolution rates, and its intensity increases with task complexity. However, it remains largely unguided: agents may focus on surface-level symptoms during localization, fail to refine near-correct patches, overlook issue requirements, and generate tests with limited behavioral diversity. To address these limitations, we propose DeskCheck, an agentic scaffold that systematically guides code reasoning throughout repository-level issue resolution. DeskCheck simulates execution paths to localiz…
- Kategoria arxiv
- cs.SE
- Kategoria
- Inżynieria oprogramowania