Principled Human-AI Collaboration in Agentic Workflows
stat.ML, cs.AI, cs.LG, stat.ME
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Cost-Sensitive Learning to Defer to Multiple Experts with Workload Constraints
- Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
- Valid Stopping in Adaptive Generator-Verifier Loops
- Optimal Stopping vs Best-of-$N$ for Inference Time Optimization
- Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks
- COOPA: A Modular LLM Agent Architecture for Operations Research Problems
- Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
- REVES: REvision and VErification--Augmented Training for Test-Time Scaling
- Contextual Online Uncertainty-Aware Preference Learning for Human Feedback
- Early Stopping Chain-of-thoughts in Large Language Models
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference