Benchmarking candidate coverage and rejection policy transfer in typed decision models

arXiv:2610.03387 · cs.AI, cs.CL · Submitted 2026-10-02 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-10-02

Updated: 2026-10-06

Comments: 29 pages, 5 figures. v2: expanded evaluation with Qwen2.5-7B-Instruct and CLINC150; added fixed-budget rejection policy transfer, three missing-answer sources, and controlled robustness analyses. Code and benchmark artifacts: https://github.com/luckykevvv/Decision_Model_Benchmark

Code: https://github.com/luckykevvv/Decision_Model_Benchmark

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmarking — 1× in this paper · explained in 3 episodes

Sources

• When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev
• Qwen2.5 Technical Report
• Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name, Not the Definition Bound to It
• Do System One Decisions Add Up? A Study of Probabilistic Coherence
• JevOut: Natural Context Can Flip Decision Models

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