# Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction

arXiv: https://arxiv.org/abs/2608.28439 · HTML: https://mlsanity.com/paper/2608.28439/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 9 of 9)

- [TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use](https://mlsanity.com/paper/2510.04550/) (2025)
- [Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction](https://mlsanity.com/paper/2605.05242/) (2026)
- [Is Grep All You Need? How Agent Harnesses Reshape Agentic Search](https://mlsanity.com/paper/2605.15184/) (2026)
- [Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation](https://mlsanity.com/paper/2603.03116/) (2026)
- [AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits](https://mlsanity.com/paper/2505.24138/) (2025)
- [DocDancer: Towards Agentic Document-Grounded Information Seeking](https://mlsanity.com/paper/2601.05163/) (2026)
- [Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases](https://mlsanity.com/paper/2603.22767/) (2026)
- [AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases](https://mlsanity.com/paper/2605.05538/) (2026)
- [Automated HEMT Model Construction from Datasheets via Multi-Modal Intelligence and Prior-Knowledge-Free Optimization](https://mlsanity.com/paper/2507.21430/) (2025)

## Abstract (arXiv)

One model passed our fidelity check without ever opening the datasheet. We found it while qualifying models for an internal extraction service: a structured-output constraint had silently disabled tool use, and the model answered anyway, with fabricated source text. Only the per-tool trace exposed it. Fidelity -- whether an extracted value matches the source -- is the standard measure for agentic document extraction, and it scores that run a success. We therefore log every tool call in an agentic benchmark of 25 hand-curated claims over three components, with 12 more on a fourth, 37 in all. From that dispatch record we build two instruments: a rule-based failure-attribution classifier, and a silent-failure detector whose two rules check only which tools were called, never the extracted value. The detector raises no flag on 207 clean fidelity-passing extractions across three model families, and recovers all 50 planted faults that withhold exactly the tools its rules check. The two results are not symmetric: the first bounds the false-positive rate, the second is recall by construction, and detection power against runs that call their tools and still answer wrongly is unmeasured. A second, independent oracle, a causal chamber that tests whether the datasheet's claims hold under physical measurement, is intentionally partial: it confirms only what the apparatus can exercise, a verifiable envelope of 2 of those 37 claims, and we give a taxonomy of why the rest are not physically gradable. Under a controlled perturbation, fidelity passes throughout while the chamber verdict flips exactly at the measurement uncertainty. Across three deployed model stacks (one destabilised by its serving stack, not by any capability gap) the tool layer buys portability and observability rather than accuracy, and earns its premium only once a document outgrows the context window.