Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems Article Swipe
Agentic artificial intelligence (AI) — multi-agent systems that combine large language models with external tools and autonomous planning — are rapidly transitioning from research laboratories into high-stakes domains. Our earlier “Basic” paper introduced a five-axis framework and proposed preliminary metrics such as goal drift and harm reduction but did not provide an algorithmic instantiation or empirical evidence. This “Advanced” sequel fills that gap. First, we revisit recent benchmarks and industrial deployments to show that technical metrics still dominate evaluations: a systematic review of 84 papers from 2023–2025 found that 83% report capability metrics while only 30% consider human-centred or economic axes[2]. Second, we formalise an Adaptive Multi-Dimensional Monitoring (AMDM) algorithm that normalises heterogeneous metrics, applies per-axis exponentially weighted moving-average thresholds and performs joint anomaly detection via the Mahalanobis distance. Third, we conduct simulations and real-world experiments. AMDM cuts anomaly-detection latency from 12.3 s to 5.6 s on simulated goal drift and reduces false-positive rates from 4.5% to 0.9% compared with static thresholds. We present a comparison table and ROC/PR curves, and we reanalyse case studies to surface missing metrics. Code, data and a reproducibility checklist accompany this paper to facilitate replication.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.21203/rs.3.rs-7497109/v1
- https://www.researchsquare.com/article/rs-7497109/latest.pdf
- OA Status
- gold
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4414142579
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414142579Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21203/rs.3.rs-7497109/v1Digital Object Identifier
- Title
-
Adaptive Monitoring and Real-World Evaluation of Agentic AI SystemsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-09-12Full publication date if available
- Authors
-
Manish ShuklaList of authors in order
- Landing page
-
https://doi.org/10.21203/rs.3.rs-7497109/v1Publisher landing page
- PDF URL
-
https://www.researchsquare.com/article/rs-7497109/latest.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.researchsquare.com/article/rs-7497109/latest.pdfDirect OA link when available
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4414142579 |
|---|---|
| doi | https://doi.org/10.21203/rs.3.rs-7497109/v1 |
| ids.doi | https://doi.org/10.21203/rs.3.rs-7497109/v1 |
| ids.openalex | https://openalex.org/W4414142579 |
| fwci | 0.0 |
| type | preprint |
| title | Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11512 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9894000291824341 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Anomaly Detection Techniques and Applications |
| topics[1].id | https://openalex.org/T12761 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9581000208854675 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Data Stream Mining Techniques |
| topics[2].id | https://openalex.org/T10400 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9174000024795532 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1705 |
| topics[2].subfield.display_name | Computer Networks and Communications |
| topics[2].display_name | Network Security and Intrusion Detection |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | doi:10.21203/rs.3.rs-7497109/v1 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.researchsquare.com/article/rs-7497109/latest.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.21203/rs.3.rs-7497109/v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5101737653 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4867-3530 |
| authorships[0].author.display_name | Manish Shukla |
| authorships[0].affiliations[0].raw_affiliation_string | Independent Researcher |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Manish A. Shukla |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | Independent Researcher |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.researchsquare.com/article/rs-7497109/latest.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11512 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9894000291824341 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Anomaly Detection Techniques and Applications |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.21203/rs.3.rs-7497109/v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.researchsquare.com/article/rs-7497109/latest.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-7497109/v1 |
| primary_location.id | doi:10.21203/rs.3.rs-7497109/v1 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.researchsquare.com/article/rs-7497109/latest.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-7497109/v1 |
| publication_date | 2025-09-12 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 34, 80, 165, 183 |
| abstract_inverted_index.s | 143, 146 |
| abstract_inverted_index.84 | 84 |
| abstract_inverted_index.We | 163 |
| abstract_inverted_index.an | 52, 105 |
| abstract_inverted_index.as | 42 |
| abstract_inverted_index.of | 83 |
| abstract_inverted_index.on | 147 |
| abstract_inverted_index.or | 55, 99 |
| abstract_inverted_index.to | 72, 144, 157, 176, 189 |
| abstract_inverted_index.we | 65, 103, 131, 172 |
| abstract_inverted_index.30% | 96 |
| abstract_inverted_index.5.6 | 145 |
| abstract_inverted_index.83% | 90 |
| abstract_inverted_index.Our | 29 |
| abstract_inverted_index.and | 16, 37, 45, 69, 121, 134, 151, 168, 171, 182 |
| abstract_inverted_index.are | 20 |
| abstract_inverted_index.but | 48 |
| abstract_inverted_index.did | 49 |
| abstract_inverted_index.not | 50 |
| abstract_inverted_index.the | 127 |
| abstract_inverted_index.via | 126 |
| abstract_inverted_index.— | 5, 19 |
| abstract_inverted_index.(AI) | 4 |
| abstract_inverted_index.0.9% | 158 |
| abstract_inverted_index.12.3 | 142 |
| abstract_inverted_index.4.5% | 156 |
| abstract_inverted_index.AMDM | 137 |
| abstract_inverted_index.This | 58 |
| abstract_inverted_index.case | 174 |
| abstract_inverted_index.cuts | 138 |
| abstract_inverted_index.data | 181 |
| abstract_inverted_index.from | 23, 86, 141, 155 |
| abstract_inverted_index.gap. | 63 |
| abstract_inverted_index.goal | 43, 149 |
| abstract_inverted_index.harm | 46 |
| abstract_inverted_index.into | 26 |
| abstract_inverted_index.only | 95 |
| abstract_inverted_index.show | 73 |
| abstract_inverted_index.such | 41 |
| abstract_inverted_index.that | 8, 62, 74, 89, 111 |
| abstract_inverted_index.this | 187 |
| abstract_inverted_index.with | 13, 160 |
| abstract_inverted_index.Code, | 180 |
| abstract_inverted_index.drift | 44, 150 |
| abstract_inverted_index.fills | 61 |
| abstract_inverted_index.found | 88 |
| abstract_inverted_index.joint | 123 |
| abstract_inverted_index.large | 10 |
| abstract_inverted_index.paper | 32, 188 |
| abstract_inverted_index.rates | 154 |
| abstract_inverted_index.still | 77 |
| abstract_inverted_index.table | 167 |
| abstract_inverted_index.tools | 15 |
| abstract_inverted_index.while | 94 |
| abstract_inverted_index.(AMDM) | 109 |
| abstract_inverted_index.First, | 64 |
| abstract_inverted_index.ROC/PR | 169 |
| abstract_inverted_index.Third, | 130 |
| abstract_inverted_index.models | 12 |
| abstract_inverted_index.papers | 85 |
| abstract_inverted_index.recent | 67 |
| abstract_inverted_index.report | 91 |
| abstract_inverted_index.review | 82 |
| abstract_inverted_index.sequel | 60 |
| abstract_inverted_index.static | 161 |
| abstract_inverted_index.Agentic | 1 |
| abstract_inverted_index.Second, | 102 |
| abstract_inverted_index.anomaly | 124 |
| abstract_inverted_index.applies | 115 |
| abstract_inverted_index.combine | 9 |
| abstract_inverted_index.conduct | 132 |
| abstract_inverted_index.curves, | 170 |
| abstract_inverted_index.earlier | 30 |
| abstract_inverted_index.latency | 140 |
| abstract_inverted_index.metrics | 40, 76, 93 |
| abstract_inverted_index.missing | 178 |
| abstract_inverted_index.present | 164 |
| abstract_inverted_index.provide | 51 |
| abstract_inverted_index.rapidly | 21 |
| abstract_inverted_index.reduces | 152 |
| abstract_inverted_index.revisit | 66 |
| abstract_inverted_index.studies | 175 |
| abstract_inverted_index.surface | 177 |
| abstract_inverted_index.systems | 7 |
| abstract_inverted_index.Adaptive | 106 |
| abstract_inverted_index.axes[2]. | 101 |
| abstract_inverted_index.compared | 159 |
| abstract_inverted_index.consider | 97 |
| abstract_inverted_index.domains. | 28 |
| abstract_inverted_index.dominate | 78 |
| abstract_inverted_index.economic | 100 |
| abstract_inverted_index.external | 14 |
| abstract_inverted_index.language | 11 |
| abstract_inverted_index.metrics, | 114 |
| abstract_inverted_index.metrics. | 179 |
| abstract_inverted_index.per-axis | 116 |
| abstract_inverted_index.performs | 122 |
| abstract_inverted_index.planning | 18 |
| abstract_inverted_index.proposed | 38 |
| abstract_inverted_index.research | 24 |
| abstract_inverted_index.weighted | 118 |
| abstract_inverted_index.accompany | 186 |
| abstract_inverted_index.algorithm | 110 |
| abstract_inverted_index.checklist | 185 |
| abstract_inverted_index.detection | 125 |
| abstract_inverted_index.distance. | 129 |
| abstract_inverted_index.empirical | 56 |
| abstract_inverted_index.evidence. | 57 |
| abstract_inverted_index.five-axis | 35 |
| abstract_inverted_index.formalise | 104 |
| abstract_inverted_index.framework | 36 |
| abstract_inverted_index.reanalyse | 173 |
| abstract_inverted_index.reduction | 47 |
| abstract_inverted_index.simulated | 148 |
| abstract_inverted_index.technical | 75 |
| abstract_inverted_index.Monitoring | 108 |
| abstract_inverted_index.artificial | 2 |
| abstract_inverted_index.autonomous | 17 |
| abstract_inverted_index.benchmarks | 68 |
| abstract_inverted_index.capability | 92 |
| abstract_inverted_index.comparison | 166 |
| abstract_inverted_index.facilitate | 190 |
| abstract_inverted_index.industrial | 70 |
| abstract_inverted_index.introduced | 33 |
| abstract_inverted_index.normalises | 112 |
| abstract_inverted_index.real-world | 135 |
| abstract_inverted_index.systematic | 81 |
| abstract_inverted_index.thresholds | 120 |
| abstract_inverted_index.2023–2025 | 87 |
| abstract_inverted_index.Mahalanobis | 128 |
| abstract_inverted_index.algorithmic | 53 |
| abstract_inverted_index.deployments | 71 |
| abstract_inverted_index.high-stakes | 27 |
| abstract_inverted_index.multi-agent | 6 |
| abstract_inverted_index.preliminary | 39 |
| abstract_inverted_index.simulations | 133 |
| abstract_inverted_index.thresholds. | 162 |
| abstract_inverted_index.“Basic” | 31 |
| abstract_inverted_index.evaluations: | 79 |
| abstract_inverted_index.experiments. | 136 |
| abstract_inverted_index.intelligence | 3 |
| abstract_inverted_index.laboratories | 25 |
| abstract_inverted_index.replication. | 191 |
| abstract_inverted_index.exponentially | 117 |
| abstract_inverted_index.heterogeneous | 113 |
| abstract_inverted_index.human-centred | 98 |
| abstract_inverted_index.instantiation | 54 |
| abstract_inverted_index.transitioning | 22 |
| abstract_inverted_index.false-positive | 153 |
| abstract_inverted_index.moving-average | 119 |
| abstract_inverted_index.“Advanced” | 59 |
| abstract_inverted_index.reproducibility | 184 |
| abstract_inverted_index.Multi-Dimensional | 107 |
| abstract_inverted_index.anomaly-detection | 139 |
| abstract_inverted_index.<title>Abstract</title> | 0 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5101737653 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 1 |
| citation_normalized_percentile.value | 0.18661588 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |