Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents

Chanjin Park

cs.AIFeb 22, 2026

Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents

Authors: Chanjin Park

Organizations: Seoul National University · Institute of Engineering Research, Seoul National University, Seoul, Korea

Abstract

Large Language Models (LLMs) are evolving into autonomous agents, yet current "frameless" development--relying on ambiguous natural language without engineering blueprints--leads to critical risks such as scope creep and open-loop failures. To ensure industrial-grade reliability, this study proposes Agentic Problem Frames (APF), a systematic engineering framework that shifts focus from internal model intelligence to the structured interaction between the agent and its environment. The APF establishes a dynamic specification paradigm where intent is concretized at runtime through domain knowledge injection. At its core, the Act-Verify-Refine (AVR) loop functions as a closed-loop control system that transforms execution results into verified knowledge assets, driving system behavior toward asymptotic convergence to mission requirements (R). To operationalize this, this study introduces the Agentic Job Description (AJD), a formal specification tool that defines jurisdictional boundaries, operational contexts, and epistemic evaluation criteria. The efficacy of this framework is validated through two contrasting case studies: a delegated proxy model for business travel and an autonomous supervisor model for industrial equipment management. By applying AJD-based specification and APF modeling to these scenarios, the analysis demonstrates how operational scenarios are systematically controlled within defined boundaries. These cases provide a conceptual proof that agent reliability stems not from a model's internal reasoning alone, but from the rigorous engineering structures that anchor stochastic AI within deterministic business processes, thereby enabling the development of verifiable and dependable domain agents.

Figures & tables

AJD Component	PF Mapping	Engineering Guidelines & Implementation Points
Mission	Requirement ( $R$ )	The final goal state to be achieved in the world ( $W$ ). [Result-Oriented] Focus on "What" rather than "How." • Define the goal state (e.g., "Prevent accident" instead of "Stop equipment") to allow for reasoning autonomy.
Workplace	World ( $W$ )	Physical/digital domains the machine interacts with. [Domain Isolation] Distinguish if the domain is Causal (API) or Biddable (User). • Define isolated side-effect boundaries for $W_{User},W_{Motor}$ , etc.
Scope	Machine ( $M$ )	Identity and jurisdictional boundaries of the machine. [Machine’s Authority] Specify permissions and negative constraints . • Use guardrails to prevent hallucinations and job deviation from the professional persona.
Operational Context	Spec ( $S$ )	Information required to transform events into execution specifications ( $S_{t}$ ). [Late Binding] Inject the following at runtime: • Contexts : Real-time domain knowledge (RAG) and Scope/Authority boundaries. • Memory : Re-injection of verified success trajectories ( $K_{\Delta}$ ). • Capabilities : Tool specifications (MCP/A2A).
Evaluation Method	Knowledge ( $K$ )	Epistemic confirmation procedures to prove mission completion. [Epistemic Grounding] Design logic to finalize action results as knowledge: • Callback : Fact verification (Physical/Digital sensor data). • Confirm : Value verification (Explicit user approval).

Table 1: Mapping Components of the AJD

AJD Item	PF Mapping	Engineering Specification ( $S$ )
Mission	Requirement ( $R$ )	[Minimize Administrative Effort] Minimize direct user intervention and cognitive effort by providing a completed itinerary through personalized scheduling and autonomous reservation.
Workplace	World ( $W$ )	• $W_{User}$ : Subject of request and the final value approval domain. • $W_{System}$ : Internal email systems, groupware (calendars), etc. • $W_{External}$ : Airlines, railway systems, and hotel reservation APIs.
Scope	Machine ( $M$ )	• [Identity] : Senior-level professionalism with deep awareness of corporate travel policies. • [Authority] : Permission for temporary bookings and submission of payment drafts within corporate limits. • [Boundary] : Strict blocking and warning for policy violations (e.g., unauthorized Business class).
Operational Context	Spec ( $S$ )	• Contexts : Meeting schedules and corporate travel reimbursement guidelines. • Memory : Historical preferences (e.g., H-hotel in Haeundae or a preferred window seat). • Capabilities : Real-time API integration for transport and accommodation via MCP.
Evaluation Method	Knowledge ( $K$ )	• Callback : Fact-checking by monitoring email for e-ticket/voucher issuance. • Confirm : Acquisition of explicit final approval from the user on the proposed itinerary.

Table 2: AJD Specification for Smart Trip Assistant

Figure 1: APF diagram for industrial smart travel agent

AJD Item	PF Mapping	Engineering Specification ( $S$ )
Mission	Requirement ( $R$ )	[Optimize Safety and Uptime] Maintain an absolute safe state at all times while minimizing unplanned downtime through proactive intervention and rapid reporting.
Workplace	World ( $W$ )	• $W_{Edge}$ : IoT Edge Agent (Intermediary for real-time sensing and control). • $W_{Digital}$ : ERP and maintenance management systems (Parts ordering and report storage). • $W_{Manager}$ : On-site safety and production managers (Final approvers).
Scope	Machine ( $M$ )	• Authority : Detection of anomalies, emergency intervention (Edge control), root cause analysis, and drafting action reports. • Constraint : Prohibition of unauthorized restarts and final payment for parts without manager approval.
Operational Context	Spec ( $S$ )	• Contexts : Equipment specifications, safety regulations, and failure diagnosis manuals. • Memory : Historical failure patterns and successful response trajectories. • Capabilities : A2A-based Edge communication and ERP system API integration.
Evaluation Method	Knowledge ( $K$ )	• Callback : Physical verification of action results (e.g., confirming RPM=0 via sensor data). • Confirm : Assetization of knowledge through final approval of parts orders and root cause analysis reports.

Table 3: AJD Specification for Industrial Safety Agent

Figure 2: APF diagram for industrial safety manager agent

AI Agent Reliability

AI agent reliability studies whether tool-using systems act correctly, consistently, safely, and recoverably across changing tasks and environments.

See all 338 papers

A Self-Healing Framework for Reliable LLM-Based Autonomous Agents
May 7, 2026Cheonsu Jeong, Younggun ShinSoftware Engineering Agents Fault Detection
AX Center, SAMSUNG SDS, Seoul, South Korea · Dept. of Artificial Intelligence, Graduate School of Engineering, Yonsei University, Seoul, South Korea
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
Jun 2, 2026Ruida Wang, Jerry Huang, Pengcheng Wang +3Software Engineering Agents Formal Verification
University of Illinois Urbana-Champaign · Independent researcher
The Auton Agentic AI Framework
Feb 27, 2026Sheng Cao, Zhao Chang, Chang Li +3Agentic AI LLM Agent Orchestration

May 7, 2026J/K move · Enter open · S save

A Self-Healing Framework for Reliable LLM-Based Autonomous Agents

Cheonsu Jeong, Younggun Shin

AX Center, SAMSUNG SDS, Seoul, South Korea · Dept. of Artificial Intelligence, Graduate School of Engineering, Yonsei University, Seoul, South Korea

Software Engineering Agents Fault Detection LLM Agent Reliability

Open paper AskPDF arXiv

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution errors, and inconsistent reasoning. This paper proposes a reliability-aware self-healing framework for LLM-based software agents. The framework integrates failure detection, reliability assessment, and automated recovery mechanisms. First, we define a taxonomy of failure types and introduce a quantitative reliability assessment model. Next, we propose a failure detection method that identifies abnormal agent behavior based on execution patterns and output consistency. Finally, we design a self-healing mechanism that dynamically recovers from failures through adaptive replanning and corrective prompting strategies. The proposed framework was implemented in a multi-agent workflow environment and evaluated using real-world task scenarios. Experimental results demonstrate that our approach significantly increases task success rates, reduces failure propagation, and enhances overall system robustness compared to existing methods. In particular, this study distinguishes itself by establishing an integrated monitoring system that combines the agent's internal reasoning process with external execution results. These findings are expected to contribute to securing the stability of advanced autonomous systems and lowering the barriers to LLM adoption in production environments.

Abstract

AI Agent Reliability

Explore similar work

A Self-Healing Framework for Reliable LLM-Based Autonomous Agents

Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory

The Auton Agentic AI Framework