# Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operations

arXiv: https://arxiv.org/abs/2608.17433 · HTML: https://mlsanity.com/paper/2608.17433/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 22 of 22)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Evaluation and Benchmarking of LLM Agents: A Survey](https://mlsanity.com/paper/2507.21504/) (2025)
- [Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents](https://mlsanity.com/paper/2503.15547/) (2025)
- [pandapower - an Open Source Python Tool for Convenient Modeling, Analysis and Optimization of Electric Power Systems](https://mlsanity.com/paper/1709.06743/) (2017)
- [AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation](https://mlsanity.com/paper/2408.00764/) (2024)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [Sufficient Context: A New Lens on Retrieval Augmented Generation Systems](https://mlsanity.com/paper/2411.06037/) (2024)
- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows](https://mlsanity.com/paper/2605.27922/) (2026)
- [Causal Inference-Based Root Cause Analysis for Online Service Systems with Intervention Recognition](https://mlsanity.com/paper/2206.05871/) (2022)
- [LLM Agents Should Employ Security Principles](https://mlsanity.com/paper/2505.24019/) (2025)
- [Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning](https://mlsanity.com/paper/2506.04625/) (2025)
- [When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents](https://mlsanity.com/paper/2606.20023/) (2026)
- [Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs](https://mlsanity.com/paper/2602.17046/) (2025)
- [Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge](https://mlsanity.com/paper/2605.08518/) (2026)
- [Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection](https://mlsanity.com/paper/2603.20313/) (2026)

## Built on by (most cited first, 1 of 1)

- [Harness-Zero: Harness Distillation via Agent-as-Harness](https://mlsanity.com/paper/2609.24974/) (2026)

## Abstract (arXiv)

LLM agents have been widely adopted to operate mission-critical infrastructure (MCI). These agents normally rely on a harness that determines what information they can access, which tools they can use, and what actions they can take. Existing systems often expose the same comprehensive harness to every task, which may not be necessary and cause resource wastes. In this paper, we focus on the identification of optimal harness configurations, and view it as a resource-matching problem between what each task requires and what the harness provides. To measure this match, we classify MCI tasks based on the mathematical representation of the underlying system and rank harness configurations by the amount and type of information they provide. We then construct task-to-harness mappings from two sources: mining research literature and measuring controlled agent execution. Leveraging the measured mapping, we propose a new harness provisioning algorithm: map-guided escalation. It begins with a task-specific harness and expands to full provision only after a failed self-check. We evaluate our method in two representative MCI tasks: in liquid cooling, it improves the agent accuracy from 0.652 under full provision to 0.715 and achieves accuracy comparable to Reflexion with 48% fewer tokens; In power grids, full provision remains accuracy-optimal, while map-based provisioning offers lower-cost alternatives. These findings show that harness provisioning follows a domain-dependent accuracy-cost Pareto frontier rather than a universal optimum.