arXiv Machine Learning October 8, 2026 By Chenyu Zhang, Rachel Luo, Boyi Li, Anjali Parashar, Marco Pavone, Apoorva Sharma

Careful Judge: Safe and Efficient Human-AI Collaborative Decision Making

Read the original on arXiv Machine Learning →

The paper introduces CARE, a calibrated adaptive rectification and escalation framework that integrates AI models with human reviewers to ensure safe, human-aligned decisions. CARE continuously learns from human feedback, improving automation while reducing the need for human queries. Experiments on driving, language, and robotics datasets show a 25–81% reduction in human queries compared to baseline methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 7

Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making

arXiv:2607. 03025v1 Announce Type: new Abstract: The use of Large Language Models (LLMs) across diverse areas of human activity-ranging from everyday tasks to safety-critical applications-aims to enhance decision-making effectiveness with minimal human feedback.

By Andreas Kouridakis, Dimitrios Patiniotis Spyropoulos, George Vouros

llms agents reinforcement-learning safety

arXiv AI

Jun 26

Human-AI Complementarity: A Goal for Amplified Oversight

arXiv:2510. 26518v2 Announce Type: replace Abstract: Human feedback is critical for aligning AI systems to human values.

By Rishub Jain, Sophie Bridgers, Lili Janzer, Rory Greig, Tian Huey Teh, Vladimir Mikulik

safety

arXiv AI

Jun 12

Strategic Decision Support for AI Agents

arXiv:2606. 12587v1 Announce Type: new Abstract: Traditionally, decision support studies how humans use machine learning models to make better decisions.

By Shayan Kiyani, Sima Noorani, George Pappas, Hamed Hassani

agents

arXiv AI

Jul 7

Aligning Language Models with Selective Prediction

arXiv:2607. 03528v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as critical decision-making components in high-stakes real-world AI systems, rendering LLM reliability a foremost practical concern.

By Gaoxiang Luo, Yifan Wu, Sinian Zhang, Aryan Deshwal, Ju Sun

llms reinforcement-learning safety

arXiv AI

Aug 11

Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

arXiv:2608. 09857v1 Announce Type: cross Abstract: Advances in advanced artificial intelligence tools have sparked research in robot autonomy, but the development of such systems has largely focused on execution rather than verifying the feasibility actions planning models propose.

By Rohan Bhagra, Mahantesh Halapannavar, Uddhav Bhattarai

llms agents robotics safety

arXiv AI

Jun 11

Models That Know How Evaluations Are Designed Score Safer

arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.

By Katharina Deckenbach, Haritz Puerto, Jonas Geiping, Sahar Abdelnabi

fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making

Human-AI Complementarity: A Goal for Amplified Oversight

Strategic Decision Support for AI Agents

Aligning Language Models with Selective Prediction

Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

Models That Know How Evaluations Are Designed Score Safer