AI & ML
When Code Works but the License Doesn't: Evaluating License Constraint Handling in Coding Agents
arXiv cs.SE0 views
arXiv:2611.23299v1 Announce Type: new Abstract: Coding agents increasingly undertake repository-level development, including dependency selection, source modification, and software deployment. However, existing evaluations prioritize functional success over licensing correctness and commercial suitability. We investigate whether agents recognize and preserve software-license constraints when developing proprietary software. Experiments across multiple agents examine permissive and copyleft licenses, missing licensing information, transitive dependencies, source modification, dual licensing, vendoring, and distribution contexts. Agent traces, repository changes, and final artifacts are evaluated against licensing ground truth. Results reveal a persistent gap between functional and licensing correctness. Agents can successfully build and test software while overlooking licensing constraints involving provenance, authorization, and distribution. Better outcomes emerge when licensing information translates into engineering actions such as dependency substitution, architectural changes, and release gating. We argue that licensing in agentic development requires contextual constraint recognition and preservation across the software lifecycle, not merely license classification.
Source:https://arxiv.org/abs/2611.23299PreviousArchitectural Design Decisions for Data Ingestion in Big Data ArchitecturesNextOptimal Development Path: An Empirical Evaluation of Tiered Dependency-Aware Sequencing
Related posts
AI Agent Observability: What to Log Before Production
0dev.to
AI Agent Evaluation: How to Test Workflows That Change Their Answers
0dev.to
paper-orchestra: A Multi-Agent Pipeline That Turns Experiment Logs Into LaTeX Submissions
0dev.to
Kerberos Through the HTTPS Tunnel: Pre-Auth Capture via the KDC Proxy
0dev.to
We checked 100 well-known sites for AI-crawler readiness: llms.txt, robots.txt, schema, sitemaps
0dev.to
We asked ChatGPT, Perplexity and Gemini which software to buy. Here's who they named first
0dev.to