SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.06271 · 2026

Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering

Jeta Sopa, Mina Farajiamiri, Tayebi Soroosh, Arasteh

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2603.06271.json · badge: /api/ran/2603.06271.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
sopajeta/RaR canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
deduplicate_and_format_sources Ran
ran; our contract draft was wrong, not the code
sopajeta/RaR/agentic_retrieval/utils.py
pointer only (licence: NOASSERTION) · get_code("e9c17abfaf588d78")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sopajeta/RaR (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_config_value Ran
ran; our contract draft was wrong, not the code
sopajeta/RaR/agentic_retrieval/utils.py
pointer only (licence: NOASSERTION) · get_code("ca8747f51ea457e7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sopajeta/RaR (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_search_params Ran
ran; our contract draft was wrong, not the code
sopajeta/RaR/agentic_retrieval/utils.py
pointer only (licence: NOASSERTION) · get_code("456e5966a0a86bdd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sopajeta/RaR (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_bad_report Ran
ran, violated the contract we drafted
sopajeta/RaR/agentic_retrieval/dataset.py
pointer only (licence: NOASSERTION) · get_code("5aa31dfe33a58449")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sopajeta/RaR (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_existing_from_json Ran
ran; our contract draft was wrong, not the code
sopajeta/RaR/agentic_retrieval/persistence.py
pointer only (licence: NOASSERTION) · get_code("e95d03854ee33187")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sopajeta/RaR (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_raw_questions Ran
ran; our contract draft was wrong, not the code
sopajeta/RaR/agentic_retrieval/dataset.py
pointer only (licence: NOASSERTION) · get_code("f819cb72cb280c2a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sopajeta/RaR (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. These systems iteratively retrieve curated domain knowledge and synthesize it into structured reports before answer selection. Although such pipelines can improve performance, their impact on reliability under model variability remains unclear. In real-world deployment, heterogeneous models may align, diverge, or synchronize errors in ways not captured by average accuracy. We evaluated 34 LLMs on 169 expert-curated publicly available radiology questions, comparing zeroshot inference with a radiology-specific multi-step agentic retrieval condition in which all models received identical structured evidence reports derived from curated radiology knowledge. Agentic inference reduced inter-model decision dispersion (median entropy 0.48→0.13; P=5.6 × 10 -9 ) and increased robustness of correctness across models (mean 0.74→0.81; P=5.6 × 10 -9 ). Majority consensus also increased overall (P=2.9 × 10 -5 ). Consensus strength and robust correctness remained strongly correlated under both inference strategies (ρ=0.88 for zero-shot; ρ=0.87 for agentic), although high agreement did not guarantee correctness. Rare highconsensus, low-robustness failures occurred under both methods (1% vs. 2%). Response verbosity showed no meaningful association with correctness. Among 572 incorrect outputs, 72% were associated with moderate or high clinically assessed severity, although inter-rater agreement was low (κ=0.02). Agentic retrieval therefore was associated with more concentrated decision distributions, stronger consensus, and higher cross-model robustness of correctness. However, coordinated failures and clinically consequential error modes persisted. These findings suggest that evaluating agentic systems through accuracy or agreement alone may not always be sufficient, and that complementary analyses of stability, cross-model robustness, and potential clinical impact are needed to characterize reliability under model variability. Model name Zero-shot Agentic P-value Accuracy (%) Total correct (n) Accuracy (%) Total correct (n) Claude-Sonnet-4.6

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.06271")
get_code_for_paper("2603.06271")
have("2603.06271")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2603.06271.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2603.06271.svg)](https://syntology.ai/paper/2603.06271)

Connect an agent — have() is free.