Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learning

• URL: http://arxiv.org/abs/2511.08301v1
• Date: Wed, 12 Nov 2025 01:51:56 GMT
• Title: Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learning
• Abstract summary: The transition from human-centric to agent-centric software development practices is disrupting existing knowledge sharing environments for software developers.<n>Traditional peer-to-peer repositories and developer communities for shared technical knowledge and best practice have witnessed dramatic drops in participation in a short period of time.<n>We introduce Spark, a novel shared agentic memory architecture which is designed to emulate the collective intelligence and know-how of human developer communities.
• Score: 0.8169615474579602
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The transition from human-centric to agent-centric software development practices is disrupting existing knowledge sharing environments for software developers. Traditional peer-to-peer repositories and developer communities for shared technical knowledge and best practice have witnessed dramatic drops in participation in a short period of time. At the same time, agentic functional equivalents are yet to emerge leaving AI agents, which already generate a significant proportion of all new software code produced, without access to repositories of valuable shared learning. In this paper, we introduce Spark, a novel shared agentic memory architecture which is designed to emulate the collective intelligence and know-how of human developer communities. Spark enables AI coding agents to both contribute to and draw from a persistent and continuously evolving experiential memory. Agents operating in the same general problem space use the Spark shared memory as a repository of new knowledge to achieve collective continual learning. We evaluate Spark as a coach for AI coding agents performing software development tasks. We demonstrate that recommendations made by Spark improve the quality of code generated by generic code generation models at varying sizes and capability tiers. Boosted by Spark, a small open-weights model with 30 billion parameters was able to match the code quality afforded by a much larger state-of-the-art model. Separately, we measure the intrinsic quality of recommendations generated by Spark against a wide range of criteria inspired by software development best practice, and achieve helpfulness levels of up to 98.2% in the top two (out of five) qualitative helpfulness bands.

Related papers

• How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests [5.6795075579540395]
  This study aims to characterize agentic pull requests (PR) in comparison to human generated PRs.<n>We first analyze how differences in merge rates between agentic and human generated PRs vary over time.<n>We then identify the types of development tasks where AI coding agents are predominantly applied.
  arXiv  Detail & Related papers  (2026-07-23T21:48:28Z)
• Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development [1.6193916818014198]
  We argue that incidental learning will not re-emerge on its own and must be consciously designed back into developer-agent interactions.<n>We present "SHIELD", a multi-agent system grounded in the notion of "agents that teach"<n>We envision a path toward learning-aware development environments where productivity and learning are complementary, not competing.
  arXiv  Detail & Related papers  (2026-07-07T10:14:44Z)
• LLMoxie: Exploring Agentic AI for Scientific Software Development [0.2708918306110244]
  Report on twenty months of practice at a university-based research software engineering (RSE) center, where RSEs embedded across astronomy, earth and climate science, agriculture, and health projects worked to close this gap.<n>We describe the recurring infrastructure, governance, and process challenges of adopting Agentic AI inside a multi-domain RSE center, describe the platform and plugin design, and distill operational lessons from real scientific software deployments.
  arXiv  Detail & Related papers  (2026-07-02T18:46:27Z)
• A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX [1.4085663724094575]
  Google has been pioneering machine learning usage across dozens of products.<n>Maintaining the multitude of model source codes in different ML frameworks and versions is a significant challenge.<n>We describe an AI-based multi-agent system that we built to support automatic migration of deep learning models into JAX-based ones.
  arXiv  Detail & Related papers  (2026-03-28T14:59:40Z)
• ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions [19.875754116636436]
  We introduce ClarEval, a framework designed to assess an agent's "Collaborative Quotient" by simulating the inherent ambiguity of human communication.<n>To quantify this capability, we propose a metric suite led by Average Turns to Clarify coders (ATC) and Key Question Coverage (KQC)<n>Our experiments on eleven state-of-the-art agents reveal a stark reality: while models like GPT-5-Coder excel at coding, they often lack the strategic communication skills required for efficient partnership.
  arXiv  Detail & Related papers  (2026-02-27T01:10:27Z)
• Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning [84.70211451226835]
  Large Language Model (LLM) Agents are constrained by a dependency on human-curated data.<n>We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data.<n>Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-11-20T05:01:57Z)
• CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy [47.1570374686203]
  Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs)<n>Current RAG methods often struggle to fully exploit knowledge during generation.<n>We propose Collaborative Chain-of-Agents, a framework designed to enhance explicitly synergy over both parametric and retrieved knowledge.
  arXiv  Detail & Related papers  (2025-08-03T10:00:38Z)
• Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [60.04362496037186]
  We present the first controlled study of developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants.<n>Our results show agents can assist developers in ways that surpass copilots.
  arXiv  Detail & Related papers  (2025-07-10T20:12:54Z)
• SWE-Bench-CL: Continual Learning for Coding Agents [0.0]
  SWE-Bench-CL is a novel continual learning benchmark built on the human-verified SWE-Bench Verified dataset.<n>By organizing GitHub issues into chronologically ordered sequences that reflect natural repository evolution, SWE-Bench-CL enables direct evaluation of an agent's ability to accumulate experience.
  arXiv  Detail & Related papers  (2025-06-13T07:11:14Z)
• Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency [0.0]
  We study how different programming activities compositions and training paradigms influence code generation effectiveness.<n>Our findings provide valuable insights for organizations seeking robust AI-driven coding solutions.
  arXiv  Detail & Related papers  (2025-05-04T14:44:27Z)
• Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance [81.05882480184587]
  We propose a computational framework of Kolb's learning cycle with Vygotsky's ZPD for autonomous agents.<n>Agent K is the 1st AI system to successfully integrate Kolb- and Vygotsky-inspired human cognitive learning.<n>With 9 gold, 8 silver, and 12 bronze medals level performance - including 4 gold and 4 silver on prize-awarding competitions - Agent K is the 1st AI system to successfully integrate Kolb- and Vygotsky-inspired human cognitive learning.
  arXiv  Detail & Related papers  (2024-11-05T23:55:23Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents [109.8507367518992]
  We introduce OpenHands, a platform for the development of AI agents that interact with the world in similar ways to a human developer.<n>We describe how the platform allows for the implementation of new agents, safe interaction with sandboxed environments for code execution, and incorporation of evaluation benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T17:50:43Z)
• The AI Community Building the Future? A Quantitative Analysis of Development Activity on Hugging Face Hub [2.595302141947391]
  We analyse development activity on the Hugging Face (HF) Hub, a popular platform for building, sharing, and demonstrating models. Activity is imbalanced between repositories; for example, over 70% of models have 0 downloads, while 1% account for 99% of downloads. We find that the community has a core-periphery structure, with a core of prolific developers and a majority of isolate developers.
  arXiv  Detail & Related papers  (2024-05-20T11:10:49Z)
• SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents [50.82665351100067]
  FlowGen is a code generation framework that emulates software process models based on multiple Large Language Model (LLM) agents. We evaluate FlowGenScrum on four benchmarks: HumanEval, HumanEval-ET, MBPP, and MBPP-ET.
  arXiv  Detail & Related papers  (2024-03-23T14:04:48Z)
• Experiential Co-Learning of Software-Developing Agents [83.34027623428096]
  Large language models (LLMs) have brought significant changes to various domains, especially in software development. We introduce Experiential Co-Learning, a novel LLM-agent learning framework. Experiments demonstrate that the framework enables agents to tackle unseen software-developing tasks more effectively.
  arXiv  Detail & Related papers  (2023-12-28T13:50:42Z)
• Comparing Software Developers with ChatGPT: An Empirical Investigation [0.0]
  This paper conducts an empirical investigation, contrasting the performance of software engineers and AI systems, like ChatGPT, across different evaluation metrics. The paper posits that a comprehensive comparison of software engineers and AI-based solutions, considering various evaluation criteria, is pivotal in fostering human-machine collaboration.
  arXiv  Detail & Related papers  (2023-05-19T17:25:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.