Humanize: Judgement Engineering for Agentic Coding

arXiv:2610.08900 · cs.AI, cs.CY · Submitted 2026-10-06 · Read on arXiv

cs.AI, cs.CY

Submitted: 2026-10-06

Updated: 2026-10-08

Code: https://github.com/PolyArch/humanize

Project page: https://nvlabs.github.io/kda5https://github.com/humanfia/hoa

Terminology

• Agentic Coding — 1× in this paper · explained in 1 episode

Sources

• K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
• LLM Critics Help Catch LLM Bugs

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems