Analysis of 13 coding agent scaffolds at pinned commits yields a 12-dimension taxonomy showing five composable loop primitives, with 11 agents combining multiple primitives instead of using one fixed structure.
Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, and Abhik Roychoudhury
3 Pith papers cite this work, alongside 4 external citations. Polarity classification is still indexing.
3
Pith papers citing it
4
external citations · OpenAlex
fields
cs.SE 3years
2026 3representative citing papers
LPO-derived Secure-Anchored task vectors raise simultaneous functional-and-secure code rates by 2.1–36 pp on six coding LLMs with near-zero inference overhead.
Auditing three performance-optimization benchmarks shows reference-patch validity collapses under cross-machine replay, rankings depend on scoring rules, and 384 of 450 replay-valid tasks are already solved by at least one public submission.
citing papers explorer
-
Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
Analysis of 13 coding agent scaffolds at pinned commits yields a 12-dimension taxonomy showing five composable loop primitives, with 11 agents combining multiple primitives instead of using one fixed structure.
-
Functional and Secure Code Generation with Task Vectors
LPO-derived Secure-Anchored task vectors raise simultaneous functional-and-secure code rates by 2.1–36 pp on six coding LLMs with near-zero inference overhead.
-
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?
Auditing three performance-optimization benchmarks shows reference-patch validity collapses under cross-machine replay, rankings depend on scoring rules, and 384 of 450 replay-valid tasks are already solved by at least one public submission.