This paper advocates a reasoning-centered perspective in which debugging systems generate, empirically challenge, and curate multiple hypotheses, treating explanations as first-class artifacts and accuracy as a constraint rather than the sole goal.
Abstract
Performance debugging in microservice systems is commonly framed as an optimization problem that seeks a single "best" root cause under accuracy-driven objectives. We argue that this framing creates an optimization trap: it obscures the reality of production environments, where evidence is incomplete, failures interact, and engineers must reason under uncertainty. This paper advocates a reasoning-centered perspective in which debugging systems generate, empirically challenge, and curate multiple hypotheses, treating explanations as first-class artifacts and accuracy as a constraint rather than the sole goal. We introduce the notion of a Reasoning Surface—a conceptual debugging artifact that maintains multiple, empirically grounded explanations and makes uncertainty and trade-offs explicit, rather than collapsing diagnosis into a single opaque result. Through an initial instantiation, we illustrate how this perspective leads to qualitatively different debugging behavior, particularly under operational stress, and argue for a shift beyond single-number leaderboards toward systems that support human-centered reasoning.
Praxist is introduced, a lineage-centered generational system that converts reproducible artifacts and evaluator outcomes into a typed evidence graph of findings, lane-structured frontiers, and agendas, and Separating local artifact construction from cohort-level evidence synthesis lets later attempts inherit validated mechanisms, unresolved claims, and useful constraints.
Jin Li, Ahmed Murtadha, Zhiying Wang et al.· 0 citations
WasmMend is presented, the first system to automatically repair Native-Wasm functional discrepancies and demonstrates the value of divergence-guided reasoning for cross-platform repair.
The scientific method has long guided empirical research in Software Engineering (SE), but the complexity of modern software systems often hinders its systematic application. This paper introduces ECLAIR, a causally grounded AI framework that integrates Large Language Models (LLMs) into every stage of the scientific process, from hypothesis generation to analysis and interpretation. ECLAIR treats LLMs as active scientific agents operating under the principles of causal inference, within a human-in-the-loop design that safeguards against the risks of unsound automated reasoning. We demonstrate the framework through a case study examining how prompt design influences code generation accuracy in two LLMs. Results show that, for both models, instruction-style, longer few-shot, and signature-augmented prompts yield small negative causal effects on accuracy, illustrating how causal reasoning provides a principled foundation for explaining why software phenomena occur. This study presents the first causally grounded structured methodology for embedding LLMs within the scientific method in SE, designed around the epistemological demands of empirical SE research, establishing a basis for rigorous AI-assisted research.
Alejandro Velasco, Daniel Rodríguez-Cárdenas, Dipin Khati et al.· 0 citations
Results show that CUA root-cause diagnosis can provide actionable repair signals rather than merely post-hoc explanations and show that CUA root-cause diagnosis can provide actionable repair signals.
Wei-Jia Zhang, Kunlun Zhu, Zeyi Liu et al.· 0 citations
While LLM-rewritten messages significantly improved subjective evaluations, with pragmatic messages rated as clearer and less cognitively demanding, these perceived gains did not translate into statistically significant improvements in objective debugging performance.
Alexandru-Radu Moraru, Shreyan Biswas, U. Gadiraju· 0 citations
An exploratory review of the emerging gray literature, which largely agrees on what a well-engineered loop contains: triggered agent runs bounded by machine-checkable stop conditions, persistent state files, verifier sub-agents, token budgets, and defined points of escalation to humans.
Jai Lal Lulla, Vahram Nersesyan, Seyedmoein Mohsenimofidi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
