AssetOpsBench

AI Agents for Industrial Asset Operations & Maintenance

A unified, open framework for building, orchestrating, and evaluating domain-specific AI agents in Industry 4.0.

📄 Paper · 🤗 Dataset · 🎮 Playground · 📢 IBM Blog · 🎥 Video · 📊 Kaggle · 🚀 Colab

</div>

[!IMPORTANT] 🎉 AssetOpsBench is officially accepted at KDD 2026 (Datasets & Benchmarks Track), Jeju, South Korea, alongside our hands-on tutorial Building Reliable Industrial Agents with MCP. See Publications for the full list of 2025–2026 work.

---

At a Glance

<table> <tr> <td align="center" width="16%"><b>9</b><br>_{Asset classes}</td> <td align="center" width="16%"><b>141+</b><br>_Scenarios</td> <td align="center" width="16%"><b>5 + 1</b><br>_{Domain agents + utility server}</td> <td align="center" width="16%"><b>2</b><br>_{Orchestration frameworks}</td> <td align="center" width="16%"><b>20+</b><br>_{University extensions}</td> <td align="center" width="16%"><b>500+</b><br>_{Competition submissions}</td> </tr> </table>

Built for: maintenance engineers, reliability specialists, facility planners, and Industry 4.0 researchers. Powered by: LLMs + Time Series Foundation Models, orchestrated over live sensor data and Industry 4.0 records (FMEA, work orders, alerts). Now with: simplified interface and native MCP (Model Context Protocol) support.

---

Quick Start

# Clone and install
git clone https://github.com/IBM/AssetOpsBench.git
cd AssetOpsBench
pip install -e .

# Try a scenario (to be enabled)
python -m assetopsbench.run --scenario "List all sensors of Chiller 6 in MAIN site"

Or jump in instantly:

• 🚀 Run on Colab — no install required (illustration of LLM Agent)
• 🎮 Try the HF Playground — interactive demo
• 📖 Read INSTRUCTIONS.md — full setup, MCP servers, plan-execute runner

[!NOTE] Active development is on main. The codebase used for various publication venues continues to be maintained on separate branches, for example, ACL 2026 IndustryAssetEQA and prior experimental work is maintained on main-0.x.

---

What is AssetOpsBench?

AssetOpsBench is a unified framework for developing, orchestrating, and evaluating domain-specific AI agents in industrial asset operations and maintenance. It provides reproducible scenarios, agent tooling, and evaluation pipelines for multi-step workflows in simulated industrial environments.

Domain-Specific MCP Servers

| MCP Servers | Important tools | |---|---| | IoT | sites, asset_ids, asset_detail, assets, find_assets_by_sensors, installed_sensors, measured_sensors, latest_reading, history, sensor_stats | | FMSR | get_failure_modes, generate_failure_modes, add_failure_modes | | TSFM | Tasks/evidence: list_tasks, profile_series, characterize_series, data_quality; model catalog: list_models, search_models, find_models, resolve_model, model_template, register_model, register_finetuned, hf_stats; feature catalog: list_features, search_features, extract_features, select_features; run/eval ledger: recipe_template, run_recipe, run_tabular_recipe, run_plan, evaluate, list_runs, list_results | | WO | Read: list_workorders, get_workorder, get_workorder_tasks, get_workorder_costs, get_workorder_actuals_vs_planned, get_workorder_kpis, get_schedule_calendar, get_my_assigned_workorders, get_failure_codes; write: generate_work_order, update_workorder, approve_workorder, assign_technician, close_workorder, cancel_workorder | | Vibration | get_vibration_data, list_vibration_sensors, compute_fft_spectrum, compute_envelope_spectrum, assess_vibration_severity, calculate_bearing_frequencies, diagnose_vibration | | Shared utility server | | | Utilities | json_reader, get_sensor_catalog, get_asset_catalog, get_failure_mode_catalog, current_date_time, current_time_english |

Five domain servers (IoT, FMSR, TSFM, WO, Vibration) plus one shared utility server, documented in full — arguments, categories, and backing services — in docs/mcp-servers.md.

The full TSFM MCP surface currently contains 41 tools covering model cards, feature cards, recipe execution, evaluation, and result/run lookup. See docs/mcp-servers.md for the complete reference.

The WO MCP surface contains 15 tools (9 read + 6 write) covering the full Maximo-style work-order lifecycle — query, create, approve, assign, close, cancel — plus costs, KPIs, and scheduling, backed by CouchDB with IBM Maximo mxwo field names. Set AOB_READONLY=1 to expose the 9 read tools only. See docs/mcp-servers.md for the complete reference.

Agent Frameworks

• Plan Execute — plan-and-execute sequential workflow to work with any LLM
• Deep Agent — planning, sub-agents, and virtual filesystem for long-horizon tasks
• Claude Agent — ReAct-based orchestrator using Claude with agent-as-tool delegation
• OpenAI Agent — ReAct-based orchestrator using OpenAI models with agent-as-tool delegation

MCP Environment

The src/ directory contains MCP servers and a plan-execute runner built on the Model Context Protocol. See INSTRUCTIONS.md for setup.

---

Example Scenarios

| Domain | Example Task | |---|---| | IoT | "List all assets in MAIN site" | | FMSR | "List known failure modes for asset class pump" | | TSFM | "Find a forecasting model for Chiller 6 and check it can be loaded" | | WO | "Generate a work order for Chiller 6 anomaly detection" |

Some tasks focus on a single domain, others are multi-step end-to-end workflows. Explore all scenarios on Hugging Face.

---

Leaderboards

• To be revised (WIP with latest models)
• Evaluated with 7 Large Language Models
• Trajectories scored using LLM Judge (Llama-4-Maverick-17B)
• 6-dimensional criteria measuring reasoning, execution, and data handling

Example: MetaAgent leaderboard

---

Publications

12+ contributions across 7 top venues in 2025–2026 from the team behind AssetOpsBench.

<details> <summary><b>⭐ KDD 2026 — Jeju, South Korea</b> (click to expand)</summary>

• [D&B] AssetOpsBench: A Benchmark for Industrial Asset Operations Agents · D. Patel, S. Lin, et al. · 📄 Paper
• [Tutorial] Building Reliable Industrial Agents with MCP: A Hands-on AssetOpsBench Tutorial for AI-Driven Operations · D. Patel, C. Shyalika, et al.

</details> <details> <summary><b>ACL 2026 - San Diego, USA</b></summary>

• [Industry] IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance · C. Shyalika, D. Patel, A. Sheth · arXiv:2604.23446

</details> <details> <summary><b>ICLR 2026 - Brazil</b></summary>

• [Main] Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring · N. Martinez, F. O'Donncha, W. M. Gifford, N. Zhou, D. C. Patel, R. Vaculin

</details> <details> <summary><b>AAAI 2026 — Singapore</b></summary>

• [Demo] AssetOpsBench-Live: Privacy-Aware Online Evaluation of Multi-Agent Performance in Industrial Operations · D. Patel, N. Zhou, S. Lin, J. T. Rayfield, C. Shyalika, S. R. Yarrabothula · 🎥 Demo
• [Main] SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search · Y. Zhang, G. Ganapavarapu, S. Jayaraman, B. Agrawal, D. Patel, A. Fokoue · 💻 Code
• [Bridge] Knowledge-Guided AI for Industrial Asset Health Monitoring · S. Lin, D. Patel
• [Tutorial] From Inception to Productization: Hands-on Lab for the Lifecycle of Multimodal Agentic AI in Industry 4.0 · C. Shyalika, S. Ahuja, S. Lin, R. Wickramarachchi, D. Patel, A. Sheth · 🌐 Website · 📊 Slides
• [Workshop(AABA4ET)] Agentic Code Generation for Heuristic Rules in Equipment Monitoring · F. Lorenzi, A. Langbridge, F. O'Donncha, J. Rayfield, B. Eck, S. Rosato

</details> <details> <summary><b>IAAI 2026 - Singapore</b></summary>

• [Deployed] Deployed AI Agents for Industrial Asset Management: CodeReAct Framework for Event Analysis and Work Order Automation · N. Zhou, D. Patel, A. Bhattacharyya
• [Emmerging] Diversity Meets Relevancy: Multi-Agent Knowledge Probing for Industry 4.0 Applications · C. Constantinides, D. Patel, S. Kimbleton, N. Garg, M. Paracha

</details> <details> <summary><b>NeurIPS 2025 — San Diego, USA</b></summary>

• [D&B Track] FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes · C. Constantinides, D. Patel, S. Lin, C. Guerrero, S. D. Patil, J. Kalagnanam · 📄 arXiv · 💻 Code
• [Social] Building Reliable Agentic Benchmarks: Insights from AssetOpsBench (invited talk, 2000+ registered) · D. Patel · [📅 Luma](h