pith. machine review for the scientific record. sign in

arxiv: 2604.05987 · v1 · submitted 2026-04-07 · 💻 cs.AI

Recognition: 1 theorem link

· Lean Theorem

Flowr -- Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains

Eranga Bandara , Ross Gore , Sachin Shetty , Piumi Siyambalapitiya , Sachini Rajapakse , Isurunima Kularathna , Pramoda Karunarathna , Ravi Mukkamala
show 10 more authors
Peter Foytik Safdar H. Bouk Abdul Rahman Xueping Liang Amin Hass Tharaka Hewa Ng Wee Keong Kasun De Zoysa Aruna Withanage Nilaan Loganathan
Authors on Pith no claims yet

Pith reviewed 2026-05-10 19:25 UTC · model grok-4.3

classification 💻 cs.AI
keywords agentic AIretail supply chainlarge language modelssupply chain automationhuman-in-the-loopworkflow decompositionsupermarket operationsdemand forecasting
0
0 comments X

The pith

Flowr automates end-to-end retail supply chain workflows in large supermarket chains by using specialized AI agents coordinated by LLMs with human oversight.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Large supermarket chains face repetitive, fragmented manual tasks in demand forecasting, procurement, supplier coordination, and inventory replenishment that limit scalability. Flowr decomposes these operations into AI agents each assigned a specific cognitive role, powered by a consortium of fine-tuned domain-specialized large language models under the direction of a central reasoning LLM. A human-in-the-loop model lets managers supervise via a Model Context Protocol interface to maintain control and accountability. Evaluation in a real large-scale chain shows this reduces manual overhead, better aligns supply with demand, and handles exceptions proactively at scales manual processes cannot reach.

Core claim

The paper claims that systematically breaking down manual supply chain workflows into specialized AI agents coordinated by fine-tuned LLMs and a central reasoning model, combined with human supervision through an MCP-enabled interface, enables reliable automation of previously human-dependent processes in large retail operations.

What carries the argument

A consortium of fine-tuned, domain-specialized large language models coordinated by a central reasoning LLM, operating within a human-in-the-loop orchestration model via the Model Context Protocol (MCP) interface.

If this is right

  • Manual coordination overhead in supply chain operations is significantly reduced.
  • Demand-supply alignment is improved through automated decision-making.
  • Proactive exception handling is enabled at scales unachievable by manual processes.
  • The approach provides a generalizable blueprint for agentic AI-driven automation in other large-scale enterprise settings.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The human oversight mechanism could be adjusted based on operational data to minimize intervention needs over time.
  • Similar agent decompositions might apply to other complex, fragmented business processes like order fulfillment or supplier management in different industries.
  • Continuous operation could accumulate data to refine the specialized models, potentially increasing automation reliability.
  • Validation in one chain opens the door to comparative studies across multiple retailers to test generalizability.

Load-bearing premise

That a consortium of fine-tuned domain-specialized LLMs coordinated by a central reasoning LLM can reliably perform accurate, context-aware decisions across fragmented real-world supply chain workflows with only occasional human intervention.

What would settle it

Running Flowr on a live multi-outlet supermarket scenario with high transaction volume and comparing the frequency of errors or delays in procurement and replenishment decisions against a matched manual team.

Figures

Figures reproduced from arXiv: 2604.05987 by Abdul Rahman, Amin Hass, Aruna Withanage, Eranga Bandara, Isurunima Kularathna, Kasun De Zoysa, Ng Wee Keong, Nilaan Loganathan, Peter Foytik, Piumi Siyambalapitiya, Pramoda Karunarathna, Ravi Mukkamala, Ross Gore, Sachini Rajapakse, Sachin Shetty, Safdar H. Bouk, Tharaka Hewa, Xueping Liang.

Figure 1
Figure 1. Figure 1: Overview of the supervised fine-tuning pipeline used to adapt a base LLM to [PITH_FULL_IMAGE:figures/full_fig_p008_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Comparison between direct human–LLM interaction and agentic AI–LLM in [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Manual supply chain replenishment workflow in large supermarket operations. [PITH_FULL_IMAGE:figures/full_fig_p012_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Flowr agentic AI workflow for automated retail supply chain management. The [PITH_FULL_IMAGE:figures/full_fig_p017_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Human supply chain manager orchestrating multiple specialized Flowr agentic [PITH_FULL_IMAGE:figures/full_fig_p021_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: LLM consortium and reasoning LLM integration flow within the Flowr frame [PITH_FULL_IMAGE:figures/full_fig_p023_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Flowr agentic workflow functions exposed through MCP servers and integrated [PITH_FULL_IMAGE:figures/full_fig_p025_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Procurement and Ordering Agent prompt demonstrating replenishment signal [PITH_FULL_IMAGE:figures/full_fig_p027_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Procurement and Ordering Agent output showing structured purchase orders [PITH_FULL_IMAGE:figures/full_fig_p029_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: DC Replenishment Planning Agent prompt demonstrating multi-constraint [PITH_FULL_IMAGE:figures/full_fig_p031_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: DC Replenishment Planning Agent output showing optimized outlet allocation [PITH_FULL_IMAGE:figures/full_fig_p033_11.png] view at source ↗
read the original abstract

Retail supply chain operations in supermarket chains involve continuous, high-volume manual workflows spanning demand forecasting, procurement, supplier coordination, and inventory replenishment, processes that are repetitive, decision-intensive, and difficult to scale without significant human effort. Despite growing investment in data analytics, the decision-making and coordination layers of these workflows remain predominantly manual, reactive, and fragmented across outlets, distribution centers, and supplier networks. This paper introduces Flowr, a novel agentic AI framework for automating end-to-end retail supply chain workflows in large-scale supermarket operations. Flowr systematically decomposes manual supply chain operations into specialized AI agents, each responsible for a clearly defined cognitive role, enabling automation of processes previously dependent on continuous human coordination. To ensure task accuracy and adherence to responsible AI principles, the framework employs a consortium of fine-tuned, domain-specialized large language models coordinated by a central reasoning LLM. Central to the framework is a human-in-the-loop orchestration model in which supply chain managers supervise and intervene across workflow stages via a Model Context Protocol (MCP)-enabled interface, preserving accountability and organizational control. Evaluation demonstrates that Flowr significantly reduces manual coordination overhead, improves demand-supply alignment, and enables proactive exception handling at a scale unachievable through manual processes. The framework was validated in collaboration with a large-scale supermarket chain and is domain-independent, offering a generalizable blueprint for agentic AI-driven supply chain automation across large-scale enterprise settings.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper introduces Flowr, an agentic AI framework for automating retail supply chain operations in large supermarket chains. It decomposes workflows (demand forecasting, procurement, supplier coordination, inventory replenishment) into specialized AI agents powered by fine-tuned domain LLMs, coordinated by a central reasoning LLM, with human oversight through a Model Context Protocol (MCP) interface. The authors assert that validation with a large supermarket chain demonstrates significant reductions in manual coordination overhead, improved demand-supply alignment, and proactive exception handling at scale.

Significance. If the performance claims were supported by rigorous evidence, the work would provide a practical, generalizable blueprint for deploying coordinated agentic systems in high-volume, fragmented enterprise operations. The human-in-the-loop design and emphasis on responsible AI principles address key deployment concerns in safety-critical domains.

major comments (1)
  1. [Abstract] Abstract: The central claim that 'Evaluation demonstrates that Flowr significantly reduces manual coordination overhead, improves demand-supply alignment, and enables proactive exception handling at a scale unachievable through manual processes' is unsupported. The manuscript contains no quantitative metrics (e.g., percentage reduction in overhead, alignment error rates, intervention counts), no experimental design details, no baselines (manual or existing automated systems), no error analysis, and no statistical comparisons. This absence makes the headline contribution unverifiable and load-bearing for the paper's contribution.

Simulated Author's Rebuttal

1 responses · 1 unresolved

We thank the referee for the thorough review and for highlighting the need for clearer support of our evaluation claims. We agree that the abstract's performance assertions require qualification given the current manuscript content and will revise to ensure claims are accurately scoped to the available evidence.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central claim that 'Evaluation demonstrates that Flowr significantly reduces manual coordination overhead, improves demand-supply alignment, and enables proactive exception handling at a scale unachievable through manual processes' is unsupported. The manuscript contains no quantitative metrics (e.g., percentage reduction in overhead, alignment error rates, intervention counts), no experimental design details, no baselines (manual or existing automated systems), no error analysis, and no statistical comparisons. This absence makes the headline contribution unverifiable and load-bearing for the paper's contribution.

    Authors: We agree that the abstract claim is overstated relative to the evidence presented. The manuscript describes a real-world validation through collaboration with a large supermarket chain, but this takes the form of a qualitative case study focused on workflow feasibility, manager oversight via the MCP interface, and observed operational improvements rather than a controlled quantitative experiment. We will revise the abstract to remove the unsupported phrasing around 'significantly reduces' and 'at a scale unachievable' and instead state that the framework was validated in a production-adjacent pilot demonstrating reduced coordination effort and proactive handling based on partner feedback. We will also expand the evaluation section to include details on the pilot scope, number of outlets involved, workflow stages tested, and qualitative metrics such as reported reduction in manual interventions. Due to commercial confidentiality, specific numerical baselines or statistical tests cannot be disclosed. These changes will align the claims with the manuscript's actual content while preserving the contribution as a practical deployment blueprint. revision: partial

standing simulated objections not resolved
  • Provision of specific quantitative metrics, error rates, baselines, or statistical comparisons, as these are restricted by confidentiality agreements with the industry partner and cannot be released even in revised form.

Circularity Check

0 steps flagged

No significant circularity: descriptive architecture with no derivations or self-referential fits

full rationale

The paper presents a high-level agentic AI framework for supply chain automation, including agent decomposition, LLM consortium coordination, and human-in-the-loop MCP interface. No equations, parameters, or quantitative derivations appear in the provided text. The evaluation claim is stated as an assertion of results from collaboration with a supermarket chain but is not derived from any fitted inputs, self-citations, or renamed patterns within the paper itself. All load-bearing elements remain external to any internal reduction, satisfying the criteria for a self-contained non-circular description.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a high-level system description with no mathematical model, fitted parameters, formal axioms, or new postulated entities; it assumes standard capabilities of LLMs and agent coordination without additional postulates.

pith-pipeline@v0.9.0 · 5647 in / 1150 out tokens · 46015 ms · 2026-05-10T19:25:14.104354+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents

    cs.AI 2026-04 unverdicted novelty 5.0

    A neurocognitive governance model formalizes a Pre-Action Governance Reasoning Loop that consults global, workflow, agent, and situational rules before each action, yielding 95% compliance accuracy with zero false esc...

Reference graph

Works this paper leans on

51 extracted references · 28 canonical work pages · cited by 1 Pith paper · 8 internal anchors

  1. [1]

    Jannelli, S

    V. Jannelli, S. Schoepf, M. Bickel, T. Netland, A. Brintrup, Agentic llms in the supply chain: Towards autonomous multi-agent consensus- seeking, International Journal of Production ResearchPublished online 21 December 2025 (2025). doi:10.1080/00207543.2025.2604311. URLhttps://arxiv.org/abs/2411.10184

    work page doi:10.1080/00207543.2025.2604311 2025

  2. [2]

    Brintrup, S

    A. Brintrup, S. Schoepf, V. Jannelli, Automating supply chain disruption monitoring via an agentic ai approach, arXiv preprint arXiv:2601.09680 (2026). URLhttps://arxiv.org/abs/2601.09680

    work page arXiv 2026

  3. [3]

    D. B. Acharya, K. Kuppan, B. Divya, Agentic ai: Autonomous intelli- gence for complex goals–a comprehensive survey, IEEE Access (2025)

    2025

  4. [4]

    Survey on Evaluation of LLM-based Agents

    A. Yehudai, L. Eden, A. Li, G. Uziel, Y. Zhao, R. Bar-Haim, A. Cohan, M. Shmueli-Scheuer, Survey on evaluation of llm-based agents, arXiv preprint arXiv:2503.16416 (2025). 39

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  5. [5]

    Raheem, G

    T. Raheem, G. Hossain, Agentic ai systems: Opportunities, challenges, and trustworthiness, in: 2025 IEEE International Conference on Electro Information Technology (eIT), IEEE, 2025, pp. 618–624

    2025

  6. [6]

    Bandi, B

    A. Bandi, B. Kongari, R. Naguru, S. Pasnoor, S. V. Vilipala, The rise of agentic ai: A review of definitions, frameworks, architectures, applica- tions, evaluation metrics, and challenges, Future Internet 17 (9) (2025) 404

    2025

  7. [7]

    Bandara, R

    E. Bandara, R. Gore, P. Foytik, S. Shetty, R. Mukkamala, A. Rahman, X. Liang, S. H. Bouk, A. Hass, S. Rajapakse, et al., A practical guide for designing, developing, and deploying production-grade agentic ai work- flows, arXiv preprint arXiv:2512.08769 (2025)

    work page arXiv 2025

  8. [8]

    Bandara, R

    E. Bandara, R. Gore, S. Shetty, S. Rajapakse, I. Kularathna, P. Karunarathna, R. Mukkamala, P. Foytik, S. H. Bouk, A. Rahman, et al., A practical guide to agentic ai transition in organizations, arXiv preprint arXiv:2602.10122 (2026)

    work page arXiv 2026

  9. [10]

    R. Gore, E. Bandara, S. Shetty, A. E. Musto, P. Rana, A. Valencia- Romero, C. Rhea, L. Tayebi, H. Richter, A. Yarlagadda, et al., Proof- of-tbi–fine-tuned vision language model consortium and openai-o3 rea- soning llm-based medical diagnosis support system for mild traumatic brain injury (tbi) prediction, arXiv preprint arXiv:2504.18671 (2025)

    work page arXiv 2025

  10. [11]

    Singh, A

    A. Singh, A. Ehtesham, S. Kumar, T. T. Khoei, Enhancing ai systems with agentic workflows patterns in large language model, in: 2024 IEEE World AI IoT Congress (AIIoT), IEEE, 2024, pp. 527–532

    2024

  11. [12]

    Model con- text contracts-mcp-enabled framework to integrate llms with blockchain smart contracts,

    E. Bandara, S. Shetty, R. Mukkamala, R. Gore, P. Foytik, S. H. Bouk, A. Rahman, X. Liang, N. W. Keong, K. De Zoysa, et al., Model con- text contracts-mcp-enabled framework to integrate llms with blockchain smart contracts, arXiv preprint arXiv:2510.19856 (2025)

    work page arXiv 2025

  12. [13]

    X. Hou, Y. Zhao, S. Wang, H. Wang, Model context protocol (mcp): Landscape, security threats, and future research directions, arXiv preprint arXiv:2503.23278 (2025). 40

    work page internal anchor Pith review arXiv 2025

  13. [14]

    M. M. Hasan, H. Li, E. Fallahzadeh, G. K. Rajbahadur, B. Adams, A. E. Hassan, Model context protocol (mcp) at first glance: Studying the secu- rity and maintainability of mcp servers, arXiv preprint arXiv:2506.13538 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  14. [15]

    Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes , April 2023 b

    S. Arora, B. Yang, S. Eyuboglu, A. Narayan, A. Hojel, I. Trummer, C. R´ e, Language models enable simple systems for generating structured views of heterogeneous data lakes, arXiv preprint arXiv:2304.09433 (2023)

    work page arXiv 2023

  15. [16]

    F. Wu, N. Zhang, S. Jha, P. McDaniel, C. Xiao, A new era in llm security: Exploring security concerns in real-world llm-based systems, arXiv preprint arXiv:2402.18649 (2024)

    work page arXiv 2024

  16. [17]

    Understanding the planning of LLM agents: A survey

    X. Huang, W. Liu, X. Chen, X. Wang, H. Wang, D. Lian, Y. Wang, R. Tang, E. Chen, Understanding the planning of llm agents: A survey, arXiv preprint arXiv:2402.02716 (2024)

    work page internal anchor Pith review arXiv 2024

  17. [18]

    LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models,

    Y. Zhang, S. Mao, T. Ge, X. Wang, A. de Wynter, Y. Xia, W. Wu, T. Song, M. Lan, F. Wei, Llm as a mastermind: A survey of strategic reasoning with large language models, arXiv preprint arXiv:2404.01230 (2024)

    work page arXiv 2024

  18. [19]

    Stan- dardization of neuromuscular reflex analysis–role of fine-tuned vision- language model consortium and openai gpt-oss reasoning llm enabled decision support system,

    E. Bandara, R. Gore, S. Shetty, R. Mukkamala, C. Rhea, A. Yarlagadda, S. Kaushik, L. De Silva, A. Maznychenko, I. Sokolowska, et al., Stan- dardization of neuromuscular reflex analysis–role of fine-tuned vision- language model consortium and openai gpt-oss reasoning llm enabled decision support system, arXiv preprint arXiv:2508.12473 (2025)

    work page arXiv 2025

  19. [20]

    gpt-oss-120b & gpt-oss-20b Model Card

    S. Agarwal, L. Ahmad, J. Ai, S. Altman, A. Applebaum, E. Arbus, R. K. Arora, Y. Bai, B. Baker, H. Bao, et al., gpt-oss-120b & gpt-oss- 20b model card, arXiv preprint arXiv:2508.10925 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  20. [21]

    Wang, A tutorial on llm reasoning: Relevant methods behind chatgpt o1, arXiv preprint arXiv:2502.10867 (2025)

    J. Wang, A tutorial on llm reasoning: Relevant methods behind chatgpt o1, arXiv preprint arXiv:2502.10867 (2025)

    work page arXiv 2025

  21. [22]

    H. Samo, K. Ali, M. Memon, F. A. Abbasi, M. Y. Koondhar, K. Dahri, Fine-tuning mistral 7b large language model for python query response and code generation: A parameter efficient approach, VAWKUM Trans- actions on Computer Sciences 12 (1) (2024) 205–217. 41

    2024

  22. [23]

    Augustin, J

    A. Augustin, J. Yi, T. Clausen, W. Townsley, A study of lora: Long range & low power networks for the internet of things, Sensors 16 (9) (2016) 1466

    2016

  23. [24]

    Dettmers, A

    T. Dettmers, A. Pagnoni, A. Holtzman, L. Zettlemoyer, Qlora: Efficient finetuning of quantized llms, Advances in Neural Information Processing Systems 36 (2024)

    2024

  24. [25]

    Reason, E

    T. Reason, E. Benbow, J. Langham, A. Gimblett, S. L. Klijn, B. Mal- colm, Artificial intelligence to automate network meta-analyses: Four case studies to evaluate the potential application of large language mod- els, PharmacoEconomics-Open (2024) 1–16

    2024

  25. [26]

    Agentsway–software development methodology for ai agents- based teams,

    E. Bandara, R. Gore, X. Liang, S. Rajapakse, I. Kularathne, P. Karunarathna, P. Foytik, S. Shetty, R. Mukkamala, A. Rahman, et al., Agentsway–software development methodology for ai agents-based teams, arXiv preprint arXiv:2510.23664 (2025)

    work page arXiv 2025

  26. [27]

    U. G. Junior, M. B. Born, A. C. Santos, R. B. Grossmann, J. V. Fack- lamm, V. A. de Castilhos, B. C. Alves, M. S. de Aguiar, Sistemas multi- agente e large language model: estudo de caso utilizando as ferramentas lm studio e langgraph, in: Workshop-Escola de Sistemas de Agentes, seus Ambientes e Aplica¸ c˜ oes (WESAAC), SBC, 2025, pp. 250–261

    2025

  27. [28]

    Towards responsi- ble and explainable ai agents with consensus-driven reasoning,

    E. Bandara, T. Hewa, R. Gore, S. Shetty, R. Mukkamala, P. Foytik, A. Rahman, S. H. Bouk, X. Liang, A. Hass, et al., Towards respon- sible and explainable ai agents with consensus-driven reasoning, arXiv preprint arXiv:2512.21699 (2025)

    work page arXiv 2025

  28. [30]

    Arous, K

    I. Arous, K. Chehbouni, Z. Cheng, B. Dossou, Llm explainability, in: Handbook of Human-Centered Artificial Intelligence, Springer, 2025, pp. 1–61

    2025

  29. [31]

    I. H. Sarker, Llm potentiality and awareness: a position paper from the perspective of trustworthy and responsible ai modeling, Discover Artificial Intelligence 4 (1) (2024) 40. 42

    2024

  30. [32]

    Dwivedi, D

    R. Dwivedi, D. Dave, H. Naik, S. Singhal, R. Omer, P. Patel, B. Qian, Z. Wen, T. Shah, G. Morgan, et al., Explainable ai (xai): Core ideas, techniques, and solutions, ACM computing surveys 55 (9) (2023) 1–33

    2023

  31. [33]

    Standardization of psychiatric diagnoses–role of fine-tuned llm consortium and openai-gpt-oss reasoning llm enabled de- cision support system,

    E. Bandara, R. Gore, A. Yarlagadda, A. H. Clayton, P. Samuel, C. K. Rhea, S. Shetty, Standardization of psychiatric diagnoses–role of fine- tuned llm consortium and openai-gpt-oss reasoning llm enabled decision support system, arXiv preprint arXiv:2510.25588 (2025)

    work page arXiv 2025

  32. [34]

    F. P. Junqueira, B. C. Reed, M. Serafini, Zab: High-performance broad- cast for primary-backup systems, in: Dependable Systems & Networks (DSN), 2011 IEEE/IFIP 41st International Conference on, IEEE, 2011, pp. 245–256

    2011

  33. [35]

    A. Ren, T. A. Syed, A. Alkhodre, A. Mehmood, Agentic ai framework for smart inventory replenishment, arXiv preprint arXiv:2511.23366 (2025). URLhttps://arxiv.org/abs/2511.23366

    work page arXiv 2025

  34. [36]

    S. Ren, J. Jin, G. Niu, Y. Liu, Multi-agent deep reinforcement learning for integrated demand forecasting and inventory optimiza- tion in sensor-enabled retail supply chains, Sensors 25 (8) (2025) 2428. doi:10.3390/s25082428. URLhttps://www.mdpi.com/1424-8220/25/8/2428

    work page doi:10.3390/s25082428 2025

  35. [37]

    B. Rolando, Retail supply chain management: A systematic literature review on risk, sustainability, and digital integration, LOGIS (Logistics, Operations and Global Integration Studies) 1 (1) (2025) 1–13

    2025

  36. [38]

    A. R. Chowdhury, A systematic review of risk-based procurement strate- gies in retail supply chains: Sourcing flexibility and vendor disruption management, American Journal of Advanced Technology and Engineer- ing Solutions 1 (01) (2025) 466–505

    2025

  37. [39]

    The Llama 3 Herd of Models

    A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Yang, A. Fan, et al., The llama 3 herd of models, arXiv preprint arXiv:2407.21783 (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  38. [40]

    B. Wang, S. Wang, Q. Ouyang, Probabilistic inference layer integration in mistral llm for accurate information retrieval (2024). 43

    2024

  39. [41]

    P. Wang, S. Bai, S. Tan, S. Wang, Z. Fan, J. Bai, K. Chen, X. Liu, J. Wang, W. Ge, et al., Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution, arXiv preprint arXiv:2409.12191 (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  40. [42]

    Shruti, A

    I. Shruti, A. Kumar, A. Seth, et al., Responsible generative ai: A com- prehensive study to explain llms, in: 2024 International Conference on Electrical, Computer and Energy Technologies (ICECET, IEEE, 2024, pp. 1–6

    2024

  41. [43]

    E. Chen, C. Lin, X. Tang, A. Xi, C. Wang, J. Lin, K. R. Koedinger, Vtu- tor: An open-source sdk for generative ai-powered animated pedagog- ical agents with multi-media output, arXiv preprint arXiv:2502.04103 (2025)

    work page arXiv 2025

  42. [44]

    Sojan, R

    A. Sojan, R. Rajan, P. Kuvaja, Monitoring solution for cloud-native devsecops, in: 2021 IEEE 6th International Conference on Smart Cloud (SmartCloud), IEEE, 2021, pp. 125–131

    2021

  43. [45]

    LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

    Y. Zheng, R. Zhang, J. Zhang, Y. Ye, Z. Luo, Z. Feng, Y. Ma, Lla- mafactory: Unified efficient fine-tuning of 100+ language models, arXiv preprint arXiv:2403.13372 (2024)

    work page internal anchor Pith review arXiv 2024

  44. [46]

    Bandara, A

    E. Bandara, A. Hass, S. Shetty, R. Mukkamala, R. Gore, A. Rahman, S. H. Bouk, Deep-stride: Automated security threat modeling with vision-language models, in: 2025 International Conference on Software, Telecommunications and Computer Networks (SoftCOM), 2025, pp. 1– 7

    2025

  45. [47]

    C. Liao, M. Sun, Z. Yang, J. Xie, K. Chen, B. Yuan, F. Wu, Z. Wang, Lohan: Low-cost high-performance framework to fine-tune 100b model on a consumer gpu, arXiv preprint arXiv:2403.06504 (2024)

    work page arXiv 2024

  46. [48]

    Ntousakis, J

    G. Ntousakis, J. J. Stephen, M. V. Le, S. S. L. Chukkapalli, T. Taylor, I. M. Molloy, F. Araujo, Securing mcp-based agent workflows, in: Pro- ceedings of the 4th Workshop on Practical Adoption Challenges of ML for Systems, 2025, pp. 50–55

    2025

  47. [49]

    Bandara, S

    E. Bandara, S. H. Bouk, S. Shetty, R. Mukkamala, A. Rahman, P. Foytik, R. Gore, X. Liang, N. W. Keong, K. De Zoysa, Sre-llama–fine- tuned meta’s llama llm, federated learning, blockchain and nft enabled 44 site reliability engineering (sre) platform for communication and net- working software services, arXiv preprint arXiv:2511.08282 (2025)

    work page arXiv 2025

  48. [50]

    E. Bandara, Procurement and ordering agent output - flowr supply chain workflow, GitHub Gist, example purchase order report generated by the Flowr Procurement and Ordering Agent, showing per-SKU order quantities with supplier selection justification, consolidated orders by supplier, total order value, delivery coverage estimates, and human review queue fo...

    2026

  49. [51]

    E. Bandara, Dc replenishment planning agent output - flowr supply chain workflow, GitHub Gist, example DC replenishment plan generated by the Flowr DC Replenishment Planning Agent, showing optimised outlet stock allocation, vehicle and route assignments, delivery time windows, route consolidation opportunities, and human review queue for high-risk stockou...

    2026

  50. [52]

    Sapkota, K

    R. Sapkota, K. I. Roumeliotis, M. Karkee, Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenges, arXiv preprint arXiv:2505.10468 (2025). URLhttps://arxiv.org/abs/2505.10468

    work page arXiv 2025

  51. [53]

    Menache, J

    I. Menache, J. Pathuri, D. Simchi-Levi, T. Linton, How generative ai improves supply chain management, Harvard Business Review 104 (1–