Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Mind the Gap: A Deployed Multi-Agent System for Documentation Maintenance

Lorenzo Masoero

Published

Nov 17, 2026

Citations

0

Trust level

Low

Usefulness score

12/100 (Low)

Extraction confidence

40% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 17, 2026

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

The available metadata is too thin to trust this as a primary source.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
12/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

Abstract

The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity. While code evolves faster than ever, customer-facing documentation often struggles to stay up to speed. As users increasingly rely on LLM-based agents that consume documentation as their primary interface, the impact of this documentation gap worsens: stale information propagates and is treated as authoritative. Signals for identifying where documentation has fallen behind already exist in abundance, both explicit (e.g., resolved support tickets revealing what documentation lacks) and implicit (e.g., code-documentation discrepancies detectable from automated loops). We deploy a multi-agent system, built around a triage agent we call "TriAgent," that continuously extracts these signals and repairs documentation drift. Over 43 days of shadow-mode operation, our system triaged 499 tickets and surfaced 92 gaps in the documentation. Using a panel of LLM judges from independent model families, 81.1% of TriAgent's verifiable assertions were correct (245 of the 302 assertions the human resolution addresses; majority of three judges); on length-comparable pairs the panel preferred TriAgent's response in 70.5% of pairs and the human engineer's in 23.2% (the rest had no judge majority). Importantly, agent- and human-sourced replies tended to be complementary, with the human often surfacing insights that were either buried within the existing documentation or missing from it entirely; our system turns each such insight into a documentation gap and, after human review, a fix. Repairing a gap measurably improved the agent's later answer: when the agent re-answered the same ticket after the repair, blinded judges preferred the post-repair answer over its own pre-repair answer 71.4% of the time (n=35). A blinded human audit confirms strong alignment on self-improvement.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity."

Evaluation Modes

partial

Llm As Judge

Includes extracted eval setup.

"The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity."

Quality Controls

missing

Not reported

No explicit QC controls found.

"The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Coding
Evaluation details
Evaluation modes
Llm As Judge
Agentic eval
Multi Agent
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity.
  • While code evolves faster than ever, customer-facing documentation often struggles to stay up to speed.
  • As users increasingly rely on LLM-based agents that consume documentation as their primary interface, the impact of this documentation gap worsens: stale information propagates and is treated as authoritative.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • The "AI revolution" has enabled teams across the technology industry to deliver software features at unprecedented velocity.
  • While code evolves faster than ever, customer-facing documentation often struggles to stay up to speed.

Why it matters for eval

  • Using a panel of LLM judges from independent model families, 81.1% of TriAgent's verifiable assertions were correct (245 of the 302 assertions the human resolution addresses; majority of three judges); on length-comparable pairs the panel…

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Llm As Judge

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.