From Social Coding to Agentic Coding: Productivity and Relational Reconfiguration in Open-Source Communities

• URL: http://arxiv.org/abs/2608.03585v1
• Date: Tue, 04 Aug 2026 12:41:32 GMT
• Title: From Social Coding to Agentic Coding: Productivity and Relational Reconfiguration in Open-Source Communities
• Abstract summary: Open-source software communities generate public knowledge and interpersonal relationships through visible collaboration.<n>We study this shift using an LLM-based multi-agent simulation with real GitHub data from 1,084 active developers.<n>Generative coding agents (CAs) are an advanced tool to improve development efficiency while shifting part of activities from public human interaction to private human-agent loops.
• Score: 5.037326192621355
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Open-source software communities are a form of digital public infrastructure that not only produces code, but also generates public knowledge and interpersonal relationships through visible collaboration. Generative coding agents (CAs) are an advanced tool to improve development efficiency while shifting part of activities from public human interaction to private human-agent loops. We study this shift using an LLM-based multi-agent simulation initialized with real GitHub data from 1,084 active developers and their repository relationships. After a warm-up with historical commits, we branch the same community state into parallel No-CA and CA conditions for 4-week simulations. CA introduction increases planned and completed tasks by 34.0% and 39.0%, respectively, and reduces median completion time from 45 to 20 minutes. However, adoption reaches only 26.0%, and the gains concentrate among developers who are already more active and well connected. CAs also restructure task execution pathways. Direct human-human interaction declines from 32.4% to 11.6%, while CA-involved modes increase to 57.3%, including 40.3% completed through CA-assisted self-loops. Public knowledge generated under CA condition also provides less support for later tasks. On a standardized retrieval benchmark, the CA corpus achieves 22.3% knowledge coverage, far below the 81.1% achieved by the real-human corpus, and requires more retrieval steps with a lower success rate. These results reveal a productivity-public knowledge tension: coding agents increase technical production, but more work shifts to agent-mediated or private loops, leaving public records less useful to future contributors.

Related papers

• Efficient Test-Time Adaptation through Human-AI Interaction [112.5131603022122]
  We propose test-time adaptation through human-agent interaction (TAHI)<n>We adapt agents to 30 individuals in two high-utility domains, writing and visual creation, on a total of 600 tasks.<n>Our agents improve solo task success by 4.5-20.9% within only tens of tasks.
  arXiv  Detail & Related papers  (2026-09-03T17:33:18Z)
• Reliable LLM-Generated Programs for High-Energy Physics Experiments through Graph-Grounded Software Knowledge [18.431539281285225]
  General-purpose large language models (LLMs) often produce unreliable programs for such tasks.<n>We organize these software relations before generation and retrieve task-relevant knowledge at inference time.<n>We evaluate a complete grounding system that combines hybrid retrieval over a heterogeneous software knowledge graph.
  arXiv  Detail & Related papers  (2026-09-01T11:35:02Z)
• DeepResearch Agent System [0.919770842662809]
  DeepResearch Agent System is a large language model system engineered for deep information retrieval, multi-step reasoning, and autonomous research tasks.<n>System supports a 128K-token context window with hierarchical attention mechanisms that yield 18.7% accuracy and 23.4% recall improvements.<n>System is fully open-sourced, including data synthesis, training, and inference code, and supports applications in academic research, business analysis, R&D support, and education.
  arXiv  Detail & Related papers  (2026-07-30T01:15:47Z)
• A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility [0.0]
  We present APS-RAG, Advanced Photon Source Retrieval Augmented Generation.<n>The retrieval engine fuses dense, sparse, and knowledge-graph channels with query-type-adaptive reciprocal-rank fusion.<n>We construct APS-Bench, a 50-question, question-answering (QA) dataset with auditable gold answers.
  arXiv  Detail & Related papers  (2026-07-27T17:01:30Z)
• Augmentation with Dilution: A Large-Scale Empirical Study of Human Contributor Ecosystems After AI Coding Agent Adoption [5.3319140556634315]
  We study how the number, composition, and behavior of human participants change following AI coding agent adoption in open-source projects.<n>Our results show that AI agent adoption does not significantly change the absolute number of human contributors.<n>We find that AI agents are not displacing human contributors, but are systematically reshaping the structure of open-source ecosystems.
  arXiv  Detail & Related papers  (2026-06-24T18:36:01Z)
• Building Digital Societies as Ecosystems: How Recognition and Repeat Relationships Sustain Cross-Community Work in Open Source [0.525685083367962]
  We measure cross-boundary collaboration in an open-source software (OSS) ecosystem by reconstructing the bipartite contributor-repository graph of 464 cybersecurity projects and 11,372 contributors active over October 2001-May 2022.
  arXiv  Detail & Related papers  (2026-05-24T13:04:24Z)
• Orchard: An Open-Source Agentic Modeling Framework [124.68499958175111]
  We present Orchard, an open-source framework for scalable agentic modeling.<n>At its core is Orchard Env, a lightweight environment service providing reusable primitives for sandbox lifecycle management.<n>On top of Orchard Env, we build three agentic modeling recipes.
  arXiv  Detail & Related papers  (2026-05-14T16:35:12Z)
• SWE-chat: Coding Agent Interactions From Real Users in the Wild [70.18158706281724]
  SWE-chat is the first large-scale dataset of real coding agent sessions collected from open-source developers in the wild.<n>The dataset currently contains 6,000 sessions, comprising more than 63,000 user prompts and 355,000 agent tool calls.
  arXiv  Detail & Related papers  (2026-04-22T17:08:19Z)
• SCUBA: Salesforce Computer Use Benchmark [63.66753028386581]
  SCUBA is a benchmark designed to evaluate computer-use agents on customer relationship management ( CRM) within the Salesforce platform.<n> SCUBA contains 300 task instances derived from real user interviews, spanning three primary personas, platform administrators, sales representatives, and service agents.<n>We benchmark a diverse set of agents under both zero-shot and demonstration-augmented settings.
  arXiv  Detail & Related papers  (2025-09-30T16:48:49Z)
• Intuition to Evidence: Measuring AI's True Impact on Developer Productivity [30.02516976149379]
  We present a comprehensive real-world evaluation of AI-assisted software development tools deployed at enterprise scale.<n>Over one year, 300 engineers across multiple teams integrated an in-house AI platform (DeputyDev) that combines code generation and automated review capabilities.
  arXiv  Detail & Related papers  (2025-09-24T02:34:11Z)
• Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving [62.71545696485824]
  We introduce AGENT KB, a universal memory infrastructure enabling seamless experience sharing across heterogeneous agent frameworks without retraining.<n>AGENT KB aggregates trajectories into a structured knowledge base and serves lightweight APIs.<n>We validate AGENT across major frameworks on GAIA, Humanity's Last Exam, GPQA, and SWE-bench.
  arXiv  Detail & Related papers  (2025-07-08T17:59:22Z)
• SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering [74.04271300772155]
  SyncMind is a framework that systematically defines the out-of-sync problem faced by large language model (LLM) agents in software engineering.<n>Based on SyncMind, we create SyncBench, a benchmark featuring 24,332 instances of agent out-of-sync scenarios in real-world CSE.
  arXiv  Detail & Related papers  (2025-02-10T19:38:36Z)

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.