pith. machine review for the scientific record. sign in

arxiv: 2604.13934 · v1 · submitted 2026-04-15 · 💻 cs.SE

Recognition: unknown

Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures

Daniel Rodriguez-Cardenas, David Nader Palacio, Denys Poshyvanyk

Authors on Pith no claims yet

Pith reviewed 2026-05-10 12:40 UTC · model grok-4.3

classification 💻 cs.SE
keywords autopoietic architecturesself-constructionsoftware development life-cyclefoundation modelsartificial lifeautonomous softwareSDLC automationPsi-Arch
0
0 comments X

The pith

Software can construct and maintain itself autonomously via autopoietic architectures.

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

The paper proposes a shift in the software development life-cycle toward self-construction, where systems evolve and maintain their own code without ongoing human direction. It draws on artificial life concepts to position autopoietic architectures, such as Psi-Arch, as a framework that integrates foundation-model reasoning for autonomous behavior. Current automation of maintenance leaves gaps that self-construction aims to close by making software self-sustaining. Readers would care because this could lower long-term costs and raise reliability once the mechanisms operate independently. The work serves as a position piece that outlines challenges and invites further research rather than delivering a finished implementation.

Core claim

The central claim is that autopoietic architectures provide a foundational framework for self-constructing software, enabling an artificial self-construction software life-cycle in which systems evolve and maintain autonomously by embedding foundation-model-based reasoning units.

What carries the argument

Autopoietic Architectures (Psi-Arch), a structure that lets software produce and regulate its own components through integrated reasoning units drawn from foundation models.

If this is right

  • Traditional maintenance approaches in the SDLC can be superseded by autonomous self-construction mechanisms.
  • Foundation models can supply the code understanding and reasoning needed for software to act on its own.
  • New architectural paradigms must be developed to support integration of reasoning units into self-producing systems.
  • Self-constructing software marks the next stage of SDLC automation.
  • Research should focus on overcoming integration challenges to realize these architectures.

Where Pith is reading between the lines

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

  • If realized, software could adapt to new environments or requirements in real time without waiting for developer updates.
  • This line of work could create direct exchanges between software engineering and artificial life studies on self-sustaining digital systems.
  • A practical next step is to construct a minimal Psi-Arch instance and test whether it can repair injected errors in its own codebase over successive runs.
  • Success would raise questions about liability and control when software modifies itself outside human oversight.

Load-bearing premise

Foundation-model-based reasoning units can be integrated into autopoietic architectures to produce fully autonomous self-construction without human intervention.

What would settle it

A working Psi-Arch prototype that independently detects a fault in its own code, generates and applies a fix, then confirms the change succeeds over multiple cycles without external input would support the claim; consistent failure to complete even one such cycle would falsify it.

Figures

Figures reproduced from arXiv: 2604.13934 by Daniel Rodriguez-Cardenas, David Nader Palacio, Denys Poshyvanyk.

Figure 1
Figure 1. Figure 1: Maintenance Paradigm Shift: a) Software Maintenance (SM) is independent from the main software, and b) SM is wrapping the main software. This canonical vision of software maintenance has permeated research methods in the software community, leaving no room for alternative approaches due to the remarkably successful use of statistical learning technologies such as transformers [55] or rein￾forcement learnin… view at source ↗
Figure 2
Figure 2. Figure 2: Autopoietic Architecture Ψ-Arch to enable artificial self-construction software life-cycle Version t=1 System Type 1 Main Software V1 Reasoning Unit Constructor Machine 3 Copy Machine 4 Control Machine Refactoring Program Repair 6 Instruction Tape 2 3 2 1 Version t=2 System Type 1 Main Software V2 Reasoning Unit Constructor Machine 3 Copy Machine 4 Control Machine Refactoring Program Repair 5 6 -Arch compo… view at source ↗
read the original abstract

Software engineering research has focused on automating maintenance and evolution processes to reduce costs and improve reliability. The emergence of foundation models (FMs) with strong code understanding and reasoning abilities offers new opportunities for autonomous software behavior. Inspired by Artificial Life (ALife), we propose a fundamental shift in the Software Development Life-Cycle (SDLC) by introducing self-construction mechanisms that enable software to evolve and maintain autonomously. This position paper explores the potential of Autopoietic Architectures, specifically Psi-Arch, as a foundational framework for self-constructing software. We first analyze the limitations of traditional maintenance approaches and identify gaps in current SDLC automation. Subsequently, we outline the core challenges in achieving self-construction, including the integration of foundation-model-based reasoning units and the establishment of novel architectural paradigms. Although this paper does not present a definitive solution, it seeks to catalyze discourse and inspire research toward a new paradigm in software engineering, one in which self-constructing software represents the next frontier in SDLC automation.

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

0 major / 2 minor

Summary. This position paper proposes a paradigm shift in the Software Development Life-Cycle (SDLC) toward autonomous self-construction, drawing inspiration from Artificial Life (ALife) to introduce autopoietic architectures—specifically Psi-Arch—as a framework enabling software to evolve and maintain itself with minimal human intervention. It critiques limitations of existing maintenance automation, highlights gaps in current approaches, and outlines challenges such as integrating foundation-model-based reasoning units, while explicitly stating that it offers no definitive solution or implementation but seeks to catalyze research in this new direction.

Significance. If the proposed research direction is pursued and the identified challenges are addressed, the work could help reframe software engineering around self-adaptive, resilient systems that lower long-term maintenance costs and improve reliability. Its primary contribution is as a conceptual position paper that synthesizes ALife concepts with foundation models to define an open research agenda, though its impact will depend on future technical realizations rather than any immediate validated advances.

minor comments (2)
  1. The term 'Psi-Arch' is referenced in the abstract and introduction without an accompanying brief definition, origin, or citation to prior work; adding this early would improve accessibility for readers outside the immediate subfield.
  2. The outline of core challenges (including FM integration into autopoietic structures) remains at a high level; even a single concrete, hypothetical scenario or mapping of autopoietic properties (self-production, self-maintenance) to software elements would strengthen the call for future research.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive and accurate summary of our position paper, including its recognition of the work as a conceptual contribution aimed at catalyzing research rather than providing an immediate implementation. The recommendation for minor revision is noted, and we will use the opportunity to improve clarity, tighten the discussion of challenges, and ensure the open research agenda is presented as effectively as possible.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The manuscript is explicitly a position paper that identifies open challenges in integrating foundation models into autopoietic architectures for self-constructing software. It contains no equations, fitted parameters, predictions, or technical derivations. The central claim is a call to explore a research direction rather than asserting that autonomous self-construction has been achieved. No load-bearing steps exist that reduce by construction to inputs, self-citations, or ansatzes. The paper is self-contained as a conceptual discussion.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The proposal rests on the unproven assumption that autopoietic self-construction can be realized in software through foundation models, without supplying definitions, evidence, or formal models for the architecture.

axioms (1)
  • domain assumption Foundation models possess sufficient code understanding and reasoning abilities to serve as the core units for autonomous self-construction in software.
    Invoked when the paper states that foundation models offer new opportunities for autonomous software behavior.
invented entities (1)
  • Psi-Arch no independent evidence
    purpose: To act as a foundational autopoietic architecture enabling self-constructing software.
    Introduced as a specific example framework without prior validation, implementation details, or independent evidence in the abstract.

pith-pipeline@v0.9.0 · 5479 in / 1322 out tokens · 33447 ms · 2026-05-10T12:40:44.439037+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

73 extracted references · 51 canonical work pages · 3 internal anchors

  1. [1]

    Artificial Life: The Proceedings of an Interdisciplinary Workshop on the Synthesis and Simulation of Living Systems

    1989. Artificial Life: The Proceedings of an Interdisciplinary Workshop on the Synthesis and Simulation of Living Systems. InArtificial Life (SFI Studies in the Sciences of Complexity), Christopher G. Langton (Ed.), Vol. VI. Addison-Wesley, Redwood City, CA

    1989

  2. [2]

    Albrecht, Filippos Christianos, and Lukas Schäfer

    Stefano V. Albrecht, Filippos Christianos, and Lukas Schäfer. 2024.Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. MIT Press. https: //www.marl-book.com

    2024

  3. [3]

    Daman Arora, Atharv Sonwane, Nalin Wadhwa, Abhav Mehrotra, Saiteja Utpala, et al. 2024. MASAI: Modular Architecture for Software-engineering AI Agents. arXiv:cs.AI/2406.11638 https://arxiv.org/abs/2406.11638

    work page arXiv 2024

  4. [4]

    Isaac Asimov. 1956. The Last Question. InScience Fiction Thinking Machines: Robots, Androids, and Computers, Groff Conklin (Ed.). Gnome Press, New York, NY, 3–17

    1956

  5. [5]

    M A Bedau. 2007. Artificial Life.Philosophy of Biology(2007), 585–603. https: //doi.org/10.1016/B978-044451543-8/50027-7

    work page doi:10.1016/b978-044451543-8/50027-7 2007

  6. [6]

    Mayuri Bhadra, Daniela Sanchez Lopera, Robert Kunzelmann, and Wolfgang Ecker. 2024. A Model-Driven Architecture Approach to Accelerate Software Code Generation. In2024 7th International Conference on Software and System Engineering (ICoSSE). 23–30. https://doi.org/10.1109/ICoSSE62619.2024.00012

    work page doi:10.1109/icosse62619.2024.00012 2024

  7. [7]

    David Bingham Brown, Michael Vaughn, Ben Liblit, and Thomas Reps. 2017. The Care and Feeding of Wild-Caught Mutants. (2017). https://doi.org/10.1145/ 3106237.3106280

    work page arXiv 2017

  8. [8]

    Sicong Cao, Xiaobing Sun, Xiaoxue Wu, David Lo, Lili Bo, et al . 2024. Snopy: Bridging Sample Denoising with Causal Graph Learning for Effective Vulnera- bility Detection. In2024 39th IEEE/ACM International Conference on Automated Software Engineering (ASE). 606–618

    2024

  9. [9]

    Yizhou Chen, Zeyu Sun, Zhihao Gong, and Dan Hao. 2024. Improving Smart Contract Security with Contrastive Learning-based Vulnerability Detection. In Proceedings of the IEEE/ACM 46th International Conference on Software Engineering (ICSE ’24). Association for Computing Machinery, New York, NY, USA, Article 156, 11 pages. https://doi.org/10.1145/3597503.3639173

    work page doi:10.1145/3597503.3639173 2024

  10. [10]

    Zimin Chen, Steve Kommrusch, Michele Tufano, Louis-Noel Pouchet, Denys Poshyvanyk, et al. 2021. SequenceR: Sequence-to-Sequence Learning for End- to-End Program Repair .IEEE Transactions on Software Engineering47, 09 (Sept. 2021), 1943–1959. https://doi.org/10.1109/TSE.2019.2940179

    work page doi:10.1109/tse.2019.2940179 2021

  11. [11]

    Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Denys Poshyvanyk, Massim- iliano Di Penta, et al. 2021. An Empirical Study on the Usage of BERT Models for Code Completion.2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR)(2021), 108–119. https://api.semanticscholar.org/ CorpusID:232222637

    2021

  12. [12]

    Alan Dorin and Susan Stepney. 2024. What Is Artificial Life To- day, and Where Should It Go?Artificial Life30, 1 (02 2024), 1–

    2024

  13. [13]

    https://doi.org/10.1162/artl_e_00435 arXiv:https://direct.mit.edu/artl/article- pdf/30/1/1/2354665/artl_e_00435.pdf

    work page doi:10.1162/artl_e_00435

  14. [14]

    Shihan Dou, Yan Liu, Haoxiang Jia, Limao Xiong, Enyu Zhou, et al. 2024. Step- Coder: Improve Code Generation with Reinforcement Learning from Compiler Feedback. https://doi.org/10.48550/arXiv.2402.01391 arXiv:2402.01391 [cs]

    work page doi:10.48550/arxiv.2402.01391 2024

  15. [15]

    Eick, T.L

    S.G. Eick, T.L. Graves, A.F. Karr, J.S. Marron, and A. Mockus. 2001. Does code decay? Assessing the evidence from change management data.IEEE Transactions on Software Engineering27, 1 (2001), 1–12. https://doi.org/10.1109/32.895984

    work page doi:10.1109/32.895984 2001

  16. [16]

    Hadeel Eladawy, Claire Le Goues, and Yuriy Brun. 2024. Automated Program Repair, What Is It Good For? Not Absolutely Nothing!. InProceedings of the IEEE/ACM 46th International Conference on Software Engineering (ICSE ’24). As- sociation for Computing Machinery, New York, NY, USA, Article 84, 13 pages. https://doi.org/10.1145/3597503.3639095

    work page doi:10.1145/3597503.3639095 2024

  17. [17]

    Yujia Fan, Sinan Wang, Zebang Fei, Yao Qin, Huaxuan Li, et al. 2024. Can Coop- erative Multi-Agent Reinforcement Learning Boost Automatic Web Testing? An Exploratory Study. In2024 39th IEEE/ACM International Conference on Automated Software Engineering (ASE). 14–26

    2024

  18. [18]

    Martin Gruber, Muhammad Firhard Roslan, Owain Parry, Fabian Scharnböck, Phil McMinn, et al. 2023. Do Automatic Test Generation Tools Generate Flaky Tests? arXiv:cs.SE/2310.05223 https://arxiv.org/abs/2310.05223

    work page arXiv 2023

  19. [19]

    Afshin Mansouri, and Yuanyuan Zhang

    Mark Harman, S. Afshin Mansouri, and Yuanyuan Zhang. 2012. Search-based software engineering: Trends, techniques and applications.ACM Comput. Surv. 45, 1, Article 11 (Dec. 2012), 61 pages. https://doi.org/10.1145/2379776.2379787

    work page doi:10.1145/2379776.2379787 2012

  20. [20]

    Gonzalez- Barahona

    Israel Herraiz, Daniel Rodriguez, Gregorio Robles, and Jesus M. Gonzalez- Barahona. 2013. The evolution of the laws of software evolution: A discussion based on a systematic literature review.ACM Comput. Surv.46, 2, Article 28 (Dec. 2013), 28 pages. https://doi.org/10.1145/2543581.2543595

    work page doi:10.1145/2543581.2543595 2013

  21. [21]

    Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, et al

    Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, et al

  22. [22]

    SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv:cs.CL/2310.06770 https://arxiv.org/abs/2310.06770

    work page internal anchor Pith review arXiv

  23. [23]

    Matthew Jin, Syed Shahriar, Michele Tufano, Xin Shi, Shuai Lu, et al. 2023. In- ferFix: End-to-End Program Repair with LLMs. http://arxiv.org/abs/2303.07263 arXiv:2303.07263 [cs]

    work page arXiv 2023

  24. [24]

    Meir Lehman. 1980. Programs, Life Cycles, and Laws of Software Evolution.Proc. IEEE(1980). https://doi.org/10.1109/PROC.1980.11805

    work page doi:10.1109/proc.1980.11805 1980

  25. [25]

    Macías-Escrivá, Rodolfo Haber, Raul Del Toro, and Vicente Hernandez

    Frank D. Macías-Escrivá, Rodolfo Haber, Raul Del Toro, and Vicente Hernandez

  26. [26]

    https://doi.org/10.1016/j.eswa.2013.07.033

    Self-adaptive systems: A survey of current approaches, research challenges and applications.Expert Systems with Applications40, 18 (2013), 7267–7279. https://doi.org/10.1016/j.eswa.2013.07.033

    work page doi:10.1016/j.eswa.2013.07.033 2013

  27. [27]

    Pradeep Kumar Mahapatro and Neelamadhab Padhy. 2024. Reviewing the Land- scape: Component-Based Software Engineering Practices and Challenges. In2024 International Conference on Emerging Systems and Intelligent Computing (ESIC). 360–365. https://doi.org/10.1109/ESIC60604.2024.10481576

    work page doi:10.1109/esic60604.2024.10481576 2024

  28. [28]

    Antonio Mastropaolo, Simone Scalabrino, Nathan Cooper, David Nader Palacio, Denys Poshyvanyk, et al . 2021. Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks. In2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE). 336–347. https://doi.org/10.1109/ ICSE43902.2021.00041

    work page arXiv 2021

  29. [29]

    1980.Autopoesis and Cognition

    Varela Francisco Maturana, Humberto. 1980.Autopoesis and Cognition. 86 pages

    1980

  30. [30]

    William Merrill, Zhaofeng Wu, Norihito Naka, Yoon Kim, and Tal Linzen. 2024. Can You Learn Semantics Through Next-Word Prediction? The Case of Entail- ment. http://arxiv.org/abs/2402.13956 arXiv:2402.13956 [cs]

    work page arXiv 2024

  31. [31]

    Mohamed Wiem Mkaouer, Marouane Kessentini, Mel Cinnéide, Shinpei Hayashi, and Kalyanmoy Deb. 2016. A robust multi-objective approach to balance severity and importance of refactoring opportunities. , 34 pages. https://doi.org/10.1007/ s10664-016-9426-8

    2016

  32. [32]

    Palacio, Carlos Bernal-Cárdenas, Daniel McCrystal, Denys Poshyvanyk, et al

    Kevin Moran, David N. Palacio, Carlos Bernal-Cárdenas, Daniel McCrystal, Denys Poshyvanyk, et al. 2020. Improving the Effectiveness of Traceability Link Recov- ery using Hierarchical Bayesian Networks. In2020 IEEE/ACM 42nd International Conference on Software Engineering (ICSE). 873–885

    2020

  33. [33]

    Manish Motwani and Yuriy Brun. 2023. Better Automatic Program Repair by Using Bug Reports and Tests Together. In2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE). 1225–1237. https://doi.org/10.1109/ ICSE48619.2023.00109

    work page arXiv 2023

  34. [34]

    David Nader-palacio, Daniel Rodríguez-cárdenas, and Jonatan Gomez. 2018. As- sessing Single-Objective Performance Convergence and Time Complexity for Refactoring Detection. InProceedings of the Genetic and Evolutionary Computa- tion Conference Companion on - GECCO ’18. 1606–1613. https://doi.org/10.1145/ 3205651.3208294

    work page arXiv 2018

  35. [35]

    John Von Neumann. 1951. The General and Logical Theory of Automata. In Cerebral Mechanisms in Behaviour—The Hixon Symposium, L.A. Jeffress (Ed.). Wiley, New York, NY, USA, 1–41

    1951

  36. [36]

    1966.Theory of Self-Reproducing Automata

    John Von Neumann. 1966.Theory of Self-Reproducing Automata. University of Illinois Press, Champaign, IL, USA

    1966

  37. [37]

    Barr, and Justyna Petke

    Leandro Oliveria de Souza, Eduardo Santana de Almeida, Paulo Anselmo da Mota Silveira Neto, Earl T. Barr, and Justyna Petke. 2025. Software Product Line Engineering via Software Transplantation.ACM Trans. Softw. Eng. Methodol.34, 2, Article 31 (Jan. 2025), 27 pages. https://doi.org/10.1145/3695987

    work page doi:10.1145/3695987 2025

  38. [38]

    Oluwaseyi Ezekiel Olorunshola and Francisca Nonyelum Ogwueleka. 2022. Re- view of System Development Life Cycle (SDLC) Models for Effective Application Delivery. InInformation and Communication Technology for Competitive Strategies (ICTCS 2020), Amit Joshi, Mufti Mahmud, Roshan G. Ragel, and Nileshsingh V. Thakur (Eds.). Springer Singapore, Singapore, 281–289

    2022

  39. [39]

    Judea Pearl. 2009. Causal inference in statistics: An overview.Statistics Surveys (2009). https://doi.org/10.1214/09-SS057

    work page doi:10.1214/09-ss057 2009

  40. [40]

    Jiahao Qiu, Xuan Qi, Hongru Wang, Xinzhe Juan, Yimin Wang, et al. 2025. Alita- G: Self-Evolving Generative Agent for Agent Generation. arXiv:cs.AI/2510.23601 https://arxiv.org/abs/2510.23601

    work page arXiv 2025

  41. [41]

    Md Mahbubur Rahman, Ira Ceka, Chengzhi Mao, Saikat Chakraborty, Baishakhi Ray, et al. 2024. Towards Causal Deep Learning for Vulnerability Detection. In Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. 1–11. https://doi.org/10.1145/3597503.3639170 arXiv:2310.07958 [cs, stat]

    work page doi:10.1145/3597503.3639170 2024

  42. [42]

    Václav Rajlich. 2014. Software evolution and maintenance. InFuture of Software Engineering Proceedings (FOSE 2014). Association for Computing Machinery, New York, NY, USA, 133–144. https://doi.org/10.1145/2593882.2593893

    work page doi:10.1145/2593882.2593893 2014

  43. [43]

    2024 , volume =

    Buvaneswari A. Ramanan, Manzoor A. Khan, and Abhinav Rao. 2024. ASPIRE: A Multi-Agent Framework for Execution-Free Code Analysis and Repair. In2024 Conference acronym ’XX, June 03–05, 2018, Woodstock, NY Rodriguez-Cardenas et al. IEEE International Conference on Big Data (BigData). IEEE, Washington, DC, USA, 8811–8813. https://doi.org/10.1109/BigData62323...

    work page doi:10.1109/bigdata62323.2024.10825553 2024

  44. [44]

    Simone Romano, Christopher Vendome, Giuseppe Scanniello, and Denys Poshy- vanyk. 2018. A Multi-study Investigation Into Dead Code.IEEE Transactions on Software Engineering(2018). https://doi.org/10.1109/TSE.2018.2842781

    work page doi:10.1109/tse.2018.2842781 2018

  45. [45]

    Hiroki Sayama and Chrystopher L. Nehaniv. 2024. Self-Reproduction and Evo- lution in Cellular Automata: 25 Years After Evoloops.Artificial Life31, 1 (Feb. 2024), 81–95. https://doi.org/10.1162/artl_a_00451

    work page doi:10.1162/artl_a_00451 2024

  46. [46]

    Saad Shafiq, Atif Mashkoor, Christoph Mayr-Dorn, and Alexander Egyed. 2021. A Literature Review of Using Machine Learning in Software Development Life Cycle Stages.IEEE Access9 (2021), 140896–140920. https://doi.org/10.1109/ ACCESS.2021.3119746

    work page arXiv 2021

  47. [47]

    Haiyang Shen, Yue Li, Desong Meng, Dongqi Cai, Sheng Qi, et al. 2025. Short- cutsBench: A Large-Scale Real-world Benchmark for API-based Agents. https: //doi.org/10.48550/arXiv.2407.00132 arXiv:2407.00132 [cs]

    work page doi:10.48550/arxiv.2407.00132 2025

  48. [48]

    Samiha Shimmi, Hamed Okhravi, and Mona Rahimi. 2025. AI-Based Software Vulnerability Detection: A Systematic Literature Review. https://doi.org/10. 48550/arXiv.2506.10280 arXiv:2506.10280 [cs]

    work page arXiv 2025

  49. [50]

    Adriana Meza Soria, Taylor Lopez, Elizabeth Seero, Negin Mashhadi, Emily Evans, et al. 2024. Characterizing Software Maintenance Meetings: Information Shared, Discussion Outcomes, and Information Captured. InProceedings of the IEEE/ACM 46th International Conference on Software Engineering (ICSE ’24). Association for Computing Machinery, New York, NY, USA,...

    work page doi:10.1145/3597503.3623330 2024

  50. [51]

    Benjamin Steenhoek, Hongyang Gao, and Wei Le. 2024. Dataflow Analysis- Inspired Deep Learning for Efficient Vulnerability Detection. InProceedings of the IEEE/ACM 46th International Conference on Software Engineering (ICSE ’24). Association for Computing Machinery, New York, NY, USA, Article 16, 13 pages. https://doi.org/10.1145/3597503.3623345

    work page doi:10.1145/3597503.3623345 2024

  51. [52]

    Bruce Toran. 2023. AutoGPT. https://github.com/Significant-Gravitas/AutoGPT

    2023

  52. [53]

    Robert R. Tucci. 2013. Introduction to Judea Pearl’s Do-Calculus. (2013). http: //arxiv.org/abs/1305.5506

    work page arXiv 2013

  53. [54]

    Michele Tufano, Fabio Palomba, Gabriele Bavota, Rocco Oliveto, Massimiliano Di Penta, et al. 2017. When and Why Your Code Starts to Smell Bad (and Whether the Smells Go Away).IEEE Transactions on Software Engineering43, 11 (2017), 1063–1088. https://doi.org/10.1109/TSE.2017.2653105

    work page doi:10.1109/tse.2017.2653105 2017

  54. [55]

    Michele Tufano, Cody Watson, Gabriele Bavota, Massimiliano Di Penta, Martin White, et al. 2018. An Empirical Investigation into Learning Bug-Fixing Patches in the Wild via Neural Machine Translation. InASE 2018. 831–836. https://doi. org/10.1145/3238147.3240732

    work page doi:10.1145/3238147.3240732 2018

  55. [56]

    and D Poshyvanyk

    Watson C Bavota G Di Penta M White M Tufano M. and D Poshyvanyk. 2018. An Empirical Investigation into Learning Bug-Fixing Patches in the Wild via Neural Machine Translation. InProceedings of 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE’18) (ASE ’18). Montpellier, France

    2018

  56. [57]

    and D Poshyvanyk

    Watson C Bavota G Di Penta M White M Tufano M. and D Poshyvanyk. 2018. Deep Learning Similarities from Different Representations of Source Code. In Proceedings of the 15th IEEE/ACM Conference on Mining Software Repositories (MSR’18) (MSR ’18). Gothenburg, Sweden

    2018

  57. [58]

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, et al

  58. [59]

    Attention Is All You Need

    Attention Is All You Need. arXiv:cs.CL/1706.03762 https://arxiv.org/abs/ 1706.03762

    work page internal anchor Pith review Pith/arXiv arXiv

  59. [60]

    Palacio, Antonio Mastropaolo, and Denys Poshyvanyk

    Alejandro Velasco, Aya Garryyeva, David N. Palacio, Antonio Mastropaolo, and Denys Poshyvanyk. 2025. Toward Neurosymbolic Program Comprehension. https://doi.org/10.48550/arXiv.2502.01806 arXiv:2502.01806 [cs]

    work page doi:10.48550/arxiv.2502.01806 2025

  60. [61]

    Shuai Wang, Pei Wang, and Dinghao Wu. 2017. Semantics-aware machine learning for function recognition in binary code. InProceedings - 2017 IEEE International Conference on Software Maintenance and Evolution, ICSME 2017. https://doi.org/10.1109/ICSME.2017.59

    work page doi:10.1109/icsme.2017.59 2017

  61. [62]

    Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, et al. 2024. Executable Code Actions Elicit Better LLM Agents. arXiv:cs.CL/2402.01030 https://arxiv.org/abs/2402.01030

    work page arXiv 2024

  62. [63]

    Yuxiang Wei, Olivier Duchenne, Jade Copet, Quentin Carbonneaux, Lingming Zhang, et al . 2025. SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution. arXiv:cs.SE/2502.18449 https://arxiv.org/ abs/2502.18449

    work page arXiv 2025

  63. [64]

    Martin White, Michele Tufano, Matías Martínez, Martin Monperrus, and Denys Poshyvanyk. 2019. Sorting and Transforming Program Repair Ingredients via Deep Learning Code Similarities. In2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER). 479–490. https: //doi.org/10.1109/SANER.2019.8668043

    work page doi:10.1109/saner.2019.8668043 2019

  64. [65]

    Martin White, Michele Tufano, Christopher Vendome, and Denys Poshyvanyk

  65. [66]

    InProceedings of the 31st IEEE/ACM International Conference on Automated Software Engineering - ASE 2016

    Deep learning code fragments for code clone detection. InProceedings of the 31st IEEE/ACM International Conference on Automated Software Engineering - ASE 2016. https://doi.org/10.1145/2970276.2970326

    work page doi:10.1145/2970276.2970326 2016

  66. [67]

    Zhaofeng Wu, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, et al. 2024. Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks. https://doi.org/10.48550/arXiv.2307.02477 arXiv:2307.02477 [cs]

    work page doi:10.48550/arxiv.2307.02477 2024

  67. [68]

    Blaise Agüera y Arcas, Jyrki Alakuijala, James Evans, Ben Laurie, Alexander Mordvintsev, et al. 2024. Computational Life: How Well-formed, Self-replicating Programs Emerge from Simple Interaction. arXiv:cs.NE/2406.19108 https: //arxiv.org/abs/2406.19108

    work page arXiv 2024

  68. [69]

    Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, et al

    John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, et al

  69. [70]

    SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

    SWE-agent: Agent-Computer Interfaces Enable Automated Software Engi- neering. arXiv:cs.SE/2405.15793 https://arxiv.org/abs/2405.15793

    work page internal anchor Pith review arXiv

  70. [71]

    Yulong Ye, Tao Chen, and Miqing Li. 2025. Distilled Lifelong Self-Adaptation for Configurable Systems. arXiv:cs.SE/2501.00840 https://arxiv.org/abs/2501.00840

    work page arXiv 2025

  71. [72]

    Quanjun Zhang, Chunrong Fang, Yang Xie, Yaxin Zhang, Yun Yang, et al

  72. [73]

    A survey on large language models for software engineering.arXiv preprint arXiv:2312.15223, 2023

    A Survey on Large Language Models for Software Engineering. arXiv:cs.SE/2312.15223 https://arxiv.org/abs/2312.15223

    work page arXiv

  73. [74]

    Wenkang Zhong, Chuanyi Li, Kui Liu, Tongtong Xu, Jidong Ge, et al . 2024. Practical Program Repair via Preference-based Ensemble Strategy. InProceedings of the IEEE/ACM 46th International Conference on Software Engineering (ICSE ’24). Association for Computing Machinery, New York, NY, USA, Article 5, 13 pages. https://doi.org/10.1145/3597503.3623310

    work page doi:10.1145/3597503.3623310 2024