mlsanityData to 7 Oct 2026

CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation

arXiv 2605.15218 ↗First posted 12 May 2026cs.AI cs.CEcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Large language models deployed for MAPDL finite-element simulation face practical reliability challenges: without structured execution control, tool encapsulation, and fault recovery, outputs may be inconsistent and task failures are common. The Agent Harness paradigm addresses this by inserting domain-specific orchestration middleware that manages tool lifecycles, workflow state, and recovery escalation. This paper presents the architecture of CAX-Agent, a lightweight agent harness purpose-built for MAPDL automation, and empirically evaluates one of its core components -- the recovery policy.CAX-Agent organizes execution into three layers -- LLM service, agent harness, and solver backend -- with a recovery ladder that escalates from deterministic rule patching through model-driven regeneration to context enrichment and human intervention. We evaluate three recovery strategies (no_recovery, rule_only, and model_only) on 50 standard structural benchmarks with three repeated runs per strategy (450 case-runs total). Two independent human raters score task completion under blind conditions; inter-rater agreement is strong (quadratic weighted Cohen's kappa = 0.84, 96 percent of score pairs within one point). Model_only achieves the best completion rate (0.9267), task score (3.59/4), total score (9.16/10), and zero-intervention rate (0.84), outperforming rule_only (0.7733, 3.17/4, 7.03/10, 0.00) and no_recovery (0.6933, 2.74/4, 5.60/10, 0.00) with large effect sizes (Cliff's delta = 0.81-0.87). The benchmark uses deliberately simple geometries to isolate recovery-policy effects; we discuss the scope of these findings and directions for broader validation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 26 references that are in the map. First posted on arXiv 12 May 2026.

Builds on

13 of 26 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution13 Apr
  2. 2025The Dual-State Architecture for Reliable LLM Agents18 Dec

Other references · 11

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Designcited by 51
  6. 2024Large Language Models for Manufacturingcited by 24
  7. 2025FEABench: Evaluating Language Models on Multiphysics Reasoning Abilitycited by 21
  8. 2025ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Structured Knowledge and Reasoningcited by 9
  9. 2025Large language model-empowered next-generation computer-aided engineeringcited by 9
  10. 2026KAIJU: An Executive Kernel for Intent-Gated Execution of LLM Agentscited by 2
  11. 2023Using a Large Language Model to generate a Design Structure Matrixcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling
  2. 2026ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation
  3. 2026AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
  4. 2026Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses
  5. 2026EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Design
  6. 2026Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems
  7. 2026StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows
  8. 2026AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation