Human-AI Collaboration & Teaming Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Effective teaming blends human intent with AI autonomy. This list covers collaborative RL, preference-based teaming, and benchmarks for human-robot and human-AI coordination.

Human-AI Collaboration & Teaming: 10 key papers

1. On the Utility of Learning about Humans for Human-AI Coordination
   Carroll et al. arXiv 2019.
2. Human-Robot Gym: Benchmarking Reinforcement Learning in Human-Robot Collaboration
   Thumm et al. arXiv 2023.
3. Collaborating with Humans without Human Data
   Strouse et al. arXiv 2021.
4. Cooperative Inverse Reinforcement Learning
   Hadfield-Menell et al. arXiv 2016.
5. Learning to Complement Humans
   Wilder et al. arXiv 2020.
6. Human-AI Collaboration in Decision-Making: Beyond Learning to Defer
   Leitão et al. arXiv 2022.
7. Maximizing BCI Human Feedback using Active Learning
   Wang et al. arXiv 2020.
8. Pragmatic-Pedagogic Value Alignment
   Fisac et al. arXiv 2017.
9. Learning to Interactively Learn and Assist
   Woodward et al. arXiv 2019.
10. Too many cooks: Bayesian inference for coordinating multi-agent collaboration
    Wang et al. arXiv 2020.

Related reading lists

• Preference Learning & Learning from Comparisons
• RL from Human Feedback (RLHF)
• Inverse Reinforcement Learning
• Multi-Agent Reinforcement Learning
• Reward Learning & Reward Modeling
• Instruction Following & Finetuning
• Active Learning & Adaptive Sampling
• Collective Intelligence