Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation

arXiv:2606.04402 · cs.AI · Submitted 2026-06-03 · Read on arXiv

cs.AI

Submitted: 2026-06-03

Updated: 2026-10-01

Terminology

• Accuracy — 2× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
• RouteLLM: Learning to Route LLMs with Preference Data
• Adaptive Test-Time Compute Allocation via Learned Heuristics over Categorical Structure
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Self-Consistency Improves Chain of Thought Reasoning in Language 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