arXiv AI August 20, 2026 By George Andrikopoulos

Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering

The article discusses how corrections made by experts to large language model (LLM) assistants often fail to persist beyond a session, framing this as an operations issue rather than a tooling one. The author, a seasoned systems engineer, maps the LLM stack onto traditional engineering components—such as frozen silicon, firmware, and persistent configuration—to highlight gaps in stochastic generation and rule retirement. From these gaps, a seven‑principle operating discipline is proposed, centered on an error loop, and illustrated with three real‑world cases, including a control that inadvertently caused the harm it was meant to prevent. The paper concludes by outlining a measurement framework and a lab study needed to validate the approach.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

Hugging Face Trending Papers

Aug 19

Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering

The paper argues that when a human corrects an LLM assistant’s mistake, the correction often disappears after the session ends, highlighting an operations issue rather than a tooling one. Drawing on thirty years of systems engineering experience, the author maps the LLM stack onto traditional hardware and software components, identifies mismatches—such as stochastic generation and lack of a retirement stage—and proposes a seven‑principle operating discipline centered on an error loop. The paper includes three real‑world cases, one of which illustrates how a control mechanism can inadvertently cause the harm it was meant to prevent, and concludes with a suggested measurement framework and a lab study to validate the approach.

llms

arXiv AI

Jul 14

AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP

arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.

By Aritra Mazumder, Nusrat jahan Lia

llms agents

arXiv AI

Jul 16

Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes

arXiv:2607. 13071v1 Announce Type: cross Abstract: Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth.

By Hiroki Tamba

llms agents

Towards Data Science

Jul 17

Context Engineering Isn’t Enough — A Loop Engineering Experiment With No LLM Inside the Loop

Everyone is talking about loop engineering, but most discussions assume an LLM sits at the center of the loop. I wanted to isolate the architecture itself.

By Emmimal P Alexander

llms benchmarks

arXiv AI

Jun 15

When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime

arXiv:2606. 14589v1 Announce Type: cross Abstract: LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools, maintaining memory, and pushing results to humans.

By Wei Wu

llms agents safety

arXiv AI

Jun 2

Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems

arXiv:2606. 01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery.

By Rahul Suresh Babu, Adarsh Agrawal

llms agents benchmarks

One email a morning, machine-written

Related stories

Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering

AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP

Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes

Context Engineering Isn’t Enough — A Loop Engineering Experiment With No LLM Inside the Loop

When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime

Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems