Governing Technical Debt in Agentic AI Systems

• URL: http://arxiv.org/abs/2605.29129v1
• Date: Wed, 27 May 2026 21:42:49 GMT
• Title: Governing Technical Debt in Agentic AI Systems
• Abstract summary: We define Agentic Technical Debt as the accumulated liability created when prompts, memory, tool schemas, orchestration graphs, control policies, and observability routines are patched faster than they can be validated, standardized, and governed.<n>We define Tax as the recurring operating burden of keeping probabilistic agent behavior within acceptable bounds.<n>We outline how managers can make both visible through lightweight dashboards and governance controls.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic AI systems are increasingly being explored as production infrastructure: they reason over multiple steps, call tools, act through workflows, and adapt through memory and feedback. These systems create governance challenges that are not fully captured by traditional software or predictive ML technical debt. We define Agentic Technical Debt as the accumulated liability created when prompts, memory, tool schemas, orchestration graphs, control policies, and observability routines are patched together faster than they can be validated, standardized, and governed. We define Stochastic Tax as the recurring operating burden of keeping probabilistic agent behavior within acceptable bounds. The distinction matters: debt is a stock of design and governance liability, while the tax is a flow of operating cost that arises because stochastic agents act through tools and workflows. We outline how managers can make both visible through lightweight dashboards and governance controls.

Related papers

• Formal Verification of Agentic Systems over Operational Data [59.98246281888422]
  Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world where they act on persistent operational data.<n>Existing approaches do not provide such system-level guarantees.<n>We study here the verification of agentic systems comprising a single LLM and a tool orchestration harness over relational operational data.
  arXiv  Detail & Related papers  (2026-08-04T13:01:30Z)
• TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents [54.08846865906602]
  We characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents.<n>We propose Tool-Aware Policy Optimization (TAPO), which exploits the parameter-determinism property of information-acquisition tools.
  arXiv  Detail & Related papers  (2026-06-04T07:15:43Z)
• VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents [57.240036084348354]
  We introduce VASO, a framework for verification-guided self-evolution of robot skill contracts.<n>VASO verifies logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications.<n>On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples.
  arXiv  Detail & Related papers  (2026-06-03T20:02:35Z)
• Modeling Agentic Technical Debt and Stochastic Tax: A Standalone Framework for Measurement, Simulation, and Dashboarding [0.0]
  This note develops a formal and managerially usable model that distinguishes Agentic Technical Debt from Tax.<n>The two constructs are related, but they are not the same: debt can amplify the tax, while the tax can remain positive even when debt is minimized.
  arXiv  Detail & Related papers  (2026-05-26T17:28:30Z)
• Redrawing the AI Map: A Theory of Accountability Boundaries in Agentic Ecosystems [0.0]
  We develop a capability-level theory of accountability-boundary placement in agentic ecosystems.<n>We argue that verification cost and responsibility transferability determine whether the execution and accountability boundaries can move together.<n>The theory explains when digital modularization extends to organizational disaggregation and when accountability keeps capabilities integrated.
  arXiv  Detail & Related papers  (2026-05-22T02:57:55Z)
• ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agents [41.517468049737936]
  Long-horizon embodied agents increasingly delegate navigation, search, approach, and manipulation to specialist executors.<n>We study task-state misalignment, a task-level consistency failure in which the planner's active stage, runtime evidence, remembered context, and delegated executor no longer justify the same next-step decision.<n>We propose ContextFlow, an inspectable alignment framework that represents stages as explicit contracts, converts runtime observations into evidence packets, and applies scoped updates.
  arXiv  Detail & Related papers  (2026-05-19T03:49:17Z)
• Going Headless? On the Boundaries of Vertical AI Firms [0.0]
  General-purpose AI agents are now unbundling that package, prompting founders and investors to advocate "going headless"<n>This article argues that going headless is correct for some firms and destructive for others.<n>It proposes a three-position taxonomy determined not by sector but by task-accountability regime.
  arXiv  Detail & Related papers  (2026-05-18T03:38:29Z)
• From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation [45.37258918150899]
  We introduce AgentChord, an agentic system that models a manipulation task as a directed task graph.<n>Before execution, this graph is enriched with anticipatory recovery branches that specify context-aware corrective behaviors.<n> Empirical studies on diverse long-horizon bimanual manipulation tasks demonstrate that AgentChord substantially improves success rates and execution efficiency.
  arXiv  Detail & Related papers  (2026-05-12T11:00:45Z)
• Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap [10.967845122224299]
  We present a comparative analysis of the Terms of Service for widely used AI coding assistants and agent-enabled development tools.<n>Our analysis reveals a consistent tendency to shift responsibility for correctness, safety, and legal compliance onto users.<n>We argue that existing policy frameworks are poorly aligned with increasingly agent-mediated and autonomous software development.
  arXiv  Detail & Related papers  (2026-05-06T06:18:59Z)
• Governance by Design: Architecting Agentic AI for Organizational Learning and Scalable Autonomy [0.3499870393443268]
  Agentic AI systems can pursue goals through multi-step planning and tool-mediated action with limited direct supervision.<n>This transition introduces tensions in implementation, scaling, and governance.<n>We show that governance is implemented through concrete architectural and working arrangements that determine what the system is allowed to do.
  arXiv  Detail & Related papers  (2026-04-17T09:03:42Z)
• When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making [68.12864562049957]
  Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning.<n>This raises a fundamental question for embodied agents: when should the agent reason, and when should it act?<n>We propose RARRL (Resource-Aware Reasoning via Reinforcement Learning), a hierarchical framework for resource-aware orchestration of embodied agents.
  arXiv  Detail & Related papers  (2026-03-17T15:38:50Z)
• Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development [42.371764229953165]
  We propose a process-oriented explainability framework that exposes how agentic decisions unfold across time, tool calls, and architectural boundaries.<n>Our approach provides intent-level telemetry that complements, rather than replaces, existing review practices.<n>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.
  arXiv  Detail & Related papers  (2026-03-03T12:55:28Z)
• Monadic Context Engineering [59.95390010097654]
  This paper introduces Monadic Context Engineering (MCE) to provide a formal foundation for agent design.<n>We demonstrate how Monads enable robust composition, how Applicatives provide a principled structure for parallel execution, and crucially, how Monad Transformers allow for the systematic composition of these capabilities.<n>This layered approach enables developers to construct complex, resilient, and efficient AI agents from simple, independently verifiable components.
  arXiv  Detail & Related papers  (2025-12-27T01:52:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.