Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development

arXiv:2604.16323v2 Announce Type: replace-cross Abstract: As autonomous coding agents become deeply embedded in software development workflows, their high operational velocity introduces a critical oversight challenge: the accumulating divergence between agentic actions and architectural intent. We term this process agentic entropy: a systemic drift that traditional code diff-based and HCXAI methods fail to capture, as they address local outputs rather than global agentic behaviour. To close this gap, we propose a process-oriented explainability framework that exposes how agentic decisions unfold across time, tool calls, and architectural boundaries. Built around three pillars (conformity seeding, reasoning monitoring, and a causal graph interface) our approach provides intent-level telemetry that complements, rather than replaces, existing review practices. We demonstrate its relevance across two user profiles: lay users engaged in vibe coding, who gain structural visibility otherwise masked by functional success; and professional developers, who gain richer contextual grounding for code review without increased overhead. By treating cognitive drift as a first-class concern alongside code quality, our framework supports the minimum level of human comprehension required for agentic oversight to remain substantive.

Related

• Process-Centric Analysis of Agentic Software Systems
• Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects
• FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning
• SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
• Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision
• The Art of Building Verifiers for Computer Use Agents

Source: arXiv cs.AI | 2026-04-22