Skip to content
AI News HubLIVE
Original source2 min read

Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent

Summary

A controlled study on a production award-travel agent finds that feeding structured tool records into the model context and re-emitting them each turn causes fidelity to collapse as table size grows, while keeping records in session state and delivering rows over a typed side channel maintains high accuracy at lower cost.

SourcearXiv Computational LinguisticsAuthor: Tung Thanh Hoang
Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 30 Oct 2026]

Title:Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent

View a PDF of the paper titled Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent, by Tung Thanh Hoang

View PDF HTML (experimental)

Abstract:When a multi-turn agent delivers a tool's structured records into the model's context and re-emits them each turn, every turn can corrupt data the tool computed correctly. We measure this in a production award-travel agent: two architectures over identical frozen payloads, lineage-matched prompts and sampling, differing only in delivery architecture. SYNTHESIS feeds full record sets into the planner's context and answers follow-ups in-head; BYPASS, the deployed system, keeps records in session state, translates follow-ups into arguments for a deterministic filter, and delivers rows over a typed side channel. Across 24 dialogues (339 scored turns per condition), BYPASS scores 92.3% of turns fully correct, SYNTHESIS 45.7% (paired gap +46.6pp [+35.7, +57.1]). Varying delivered-table size by capture date, SYNTHESIS collapses from near-perfect at 10 rows or fewer to 8% or less beyond about 74 rows. On a content-controlled prefix ladder the collapse threshold orders by model capability, from under 10 rows (GPT-4o-mini) to about 198 or more (Gemini 2.5 Pro), while BYPASS stays size-flat for all four models. The collapse is expensive: beyond 100 rows, where almost no SYNTHESIS answer is correct, each correct one costs roughly 200x BYPASS's flat \$0.012. Practitioners converged on typed side-channel delivery for rendering, not correctness; we show it was, unknowingly, also a correctness decision.

Comments: Non-archival paper at the Second Workshop for Research on Agent Language Models (REALM) at EMNLP 2026. 21 pages, 5 figures

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.00442 [cs.CL]

(or arXiv:2611.00442v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.00442

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Tung Hoang [view email] [v1] Fri, 30 Oct 2026 22:50:32 UTC (142 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent, by Tung Thanh Hoang

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs cs.AI

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • BYPASS architecture scores 92.3% fully correct turns versus 45.7% for SYNTHESIS across 24 dialogues, a paired gap of +46.6pp.
  • SYNTHESIS collapses from near-perfect at 10 rows or fewer to 8% or less beyond about 74 rows; the threshold rises with model capability.
  • Beyond 100 rows, each correct SYNTHESIS answer costs roughly 200x BYPASS's flat $0.012.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Agents