Showing 2026Show all
2 papers · 1 filter
cs.SE2026
When Does Restricting a Coding Agent to execute_code Help? A Regime Agent-Design Ablation
Hong Yang, Qi Yu, Travis Desell
Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims…
cs.LG2026
Beyond the Class Subspace: Teacher-Guided Training for Reliable Out-of-Distribution Detection in Single-Domain Models
Hong Yang, Devroop Kar, Qi Yu +2
Out-of-distribution (OOD) detection methods perform well on multi-domain benchmarks, yet many practical systems are trained on single-domain data. We show that this regime induces…