Showing cs.SEShow all
3 papers · 1 filter
cs.SE2026
Architecture as Capability Equalizer for Coding Agents
Arquimedes Canedo
LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture specifications affects the quality…
cs.SE2026
Oracles That Cannot Fail: Anchoring and the Expectation That Moves With the Fault
Arquimedes Canedo
A test oracle that obtains its expected value from the system it is judging cannot fail. If a fault moves measurement and expectation together the comparison cancels exactly, and n…
cs.SE2026
Self-Reflective APIs: Structure Beats Verbosity for AI Agent Recovery
Arquimedes Canedo, Grama Chethan
When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on validation failure, a m…