Human-AI Collaboration

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

24 new papers

A weekly snapshot of new work published in Human-AI Collaboration.

Period ending 2026-09-14

8 new papers

A weekly snapshot of new work published in Human-AI Collaboration.

Period ending 2026-09-07

24 new papers

A weekly snapshot of new work published in Human-AI Collaboration.

Inside this field

Focused directions

Focused topic

Human

Within Human-AI Collaboration

185 papersExplore

Focused topic

Human-Ai Collaboration

Within Human-AI Collaboration

157 papersExplore

Focused topic

Human Oversight

Within Human-AI Collaboration

157 papersExplore

Focused topic

Human-Ai Interaction

Within Human-AI Collaboration

72 papersExplore

Focused topic

Anthropomorphism

Within Human-AI Collaboration

26 papersExplore

Focused topic

Human-Centered Framework

Within Human-AI Collaboration

26 papersExplore

577 papers

Latest in Human-AI Collaboration

Browse all topics →

When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees
May 9, 2026Dongxin Guo, Jikun Wu, Siu-Ming YiuHuman-Ai Collaboration Impossibility
PLACO: A Multi-Stage Framework for Cost-Effective Performance in Human-AI Teams
May 8, 2026Pranavkumar Mallela, Vinay Kumar, Shashi Shekhar Jha +1Human-Ai Collaboration Bayesian
How Value Induction Reshapes LLM Behaviour
May 8, 2026Arnav Arora, Natalie Schluter, Katherine Metcalf +1Human Values Large Language Model Safety
Sycophantic AI makes human interaction feel more effortful and less satisfying over time
May 8, 2026Lujain Ibrahim, Franziska Sofia Hafner, Myra Cheng +5Sycophancy Human-Ai Interaction
Eigenism: Ethics for a Human-AI Future
May 8, 2026Dan HendrycksEthics Artificial Intelligence Alignment
Post-training makes large language models less human-like
May 8, 2026Marcel Binz, Elif Akata, Abdullah Almaatouq +76Large Language Model Post-Training Large Language Model Performance
HBEE: Human Behavioral Entropy Engine -- Pre-Registered Multi-Agent LLM Simulation of Peer-Suspicion-Based Detection Inversion
May 8, 2026Vickson FerrelThreat Models Artificial Intelligence Detection
The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment
May 8, 2026William Brach, Federico Torrielli, Stine Lyngsø Beltoft +3Openclaw Emergence
InsHuman: Towards Natural and Identity-Preserving Human Insertion
May 8, 2026Jie Li, Shulian Zhang, Yangyang Gao +4Portraits Large-Scale Image Generation
UniISP: A Unified ISP Framework for Both Human and Machine Vision
May 8, 2026Hanxi Li, Yao Cheng, Bo Zhang +1Image Processing Computer Vision
Task-Oriented Communication for Human Action Understanding via Edge-Cloud Co-Inference
May 8, 2026Jingyi Liu, Cheng Yuan, Lijun He +2Edge Computing Open-Vocabulary Action Recognition
Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration
May 8, 2026Junjie Xu, Xingjiao Wu, Zihao Zhang +6Human-Ai Collaboration Affective Computing
Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
May 8, 2026Nikhilesh Prabhakar, Varun Balaji, Athresh Karanam +2Imitation Learning Neuro-Symbolic Framework
Reflections and New Directions for Human-Centered Large Language Models
May 7, 2026Caleb Ziems, Dora Zhao, Rose E. Wang +55Human-Centered Framework Natural Language Processing
Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
May 7, 2026Sixing Chen, Ji-An Li, Saner Cakir +3Large Language Model Planning Large Language Model Reasoning
AI co-mathematician: Accelerating mathematicians with agentic AI
May 7, 2026Daniel Zheng, Ingrid von Glehn, Yori Zwols +15Mathematics Human-Ai Collaboration
Ex Ante Evaluation of AI-Induced Idea Diversity Collapse
May 7, 2026Nafis Saami Azad, Raiyan Abdul BatenCreativity Artificial Intelligence Evaluation
Process Matters more than Output for Distinguishing Humans from Machines
May 7, 2026Milena Rmus, Mathew D. Hardy, Thomas L. Griffiths +1Human Oversight Cognitive Science
HumanNet: Scaling Human-centric Video Learning to One Million Hours
May 7, 2026Yufan Deng, Daquan ZhouHuman-To-Robot Transfer Human
Human-AI Co-Evolution and Epistemic Collapse: A Dynamical Systems Perspective
May 7, 2026Xuening Wu, Yanlan Kang, Qianya Xu +5Human-Ai Collaboration Emergence
AI-Generated Images: What Humans and Machines See When They Look at the Same Image
May 7, 2026Silvia Poletti, Justin Ilyes, Marcel Hasenbalg +2Ai-Generated Image Detection Generative Artificial Intelligence
PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
May 7, 2026Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim +5Red-Teaming Human-Ai Collaboration
Intentionality is a Design Decision: Measuring Functional Intentionality for Accountable AI Systems
May 6, 2026Allessia Chiappetta, Robert MahariArtificial Intelligence Governance Goal-Directed Behavior
Counterargument for Critical Thinking as Judged by AI and Humans
May 6, 2026Tosin Adewumi, Marcus Liwicki, Foteini Simistira Liwicki +3Generative Artificial Intelligence Critique
Active Contact Sensing for Robust Robot-to-Human Object Handover
May 6, 2026Linfeng Li, Lin Shao, David HsuDexterous Robot Hands Human-To-Robot Transfer
DAO-enabled decentralized physical AI: A new paradigm for human-machine collaboration
May 6, 2026Mark C. Ballandies, Florian Spychiger, Uwe Serdült +1Decentralization Human-Ai Collaboration
Can LLMs Emulate Human Belief Dynamics?
May 5, 2026Adiba Mahbub Proma, Neeley Pate, James N. Druckman +3User Simulation Belief
Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
May 5, 2026Shinas Shaji, Teena Chakkalayil Hassan, Sebastian Houben +1Human-Ai Collaboration Human-Robot Collaboration
AI Advocate: Educational Path to Transform Squads to the Future
May 5, 2026Carla Soares, Gabriel Moreira, Ana Paula Camargo +3Human-Ai Collaboration Education
A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environments
May 5, 2026Sergio Mendoza, Cedric Bhihe, Natalia Zamora +5High-Performance Computing Human-Ai Collaboration
An Ethical eValuation Agent (EeVA): Results of a Proof-of-Concept Test on a Prototype Agentic-like Workflow to Assist Ethical Deliberations
May 5, 2026Stephen Milford, B. Zara Malgir, Miguel VazquezEthics Agentic Workflows
Dynamic In-Group Persona Generation for Enhancing Human-AI Rapport
May 5, 2026Yoonseok Oh, Inseo Jung, Jinkyu Kim +3Human-Ai Interaction Persona
Human-Provenance Verification should be Treated as Labor Infrastructure in AI-Saturated Markets
May 4, 2026Erin McGurk, David KhachaturovArtificial Intelligence Governance Human Oversight
Approaching human parity in the quality of automated organoid image segmentation
May 4, 2026Chase Cartwright, Gongbo Guo, Sai Teja Pusuluri +3Medical Image Segmentation Tissue Architecture
HAAS: A Policy-Aware Framework for Adaptive Task Allocation Between Humans and Artificial Intelligence Systems
May 4, 2026Vicente Pelechano, Antoni Mestre, Manoli Albert +1Human-Ai Collaboration Artificial Intelligence Governance
AIs and Humans with Agency
May 4, 2026David MumfordHuman Oversight Artificial Intelligence Agents
Fuzzy Fingerprinting Encoder Pre-trained Language Models for Emotion Recognition in Conversations: Human Assessment and Validity Study
May 4, 2026Patrícia Pereira, Helena Moniz, Joao Paulo CarvalhoEmotion Recognition Fingerprint
Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective
May 3, 2026Hengyu Liu, Tianyi Li, Zhihong Cui +5Human-Ai Collaboration Epistemic Actions
Human-Less LLM Serving: Quantifying the Human Tax on Throughput
May 3, 2026Jianhui Lian, Li Chen, Dan Li +1Throughput Large Language Model Serving
Less Interaction But More Explanation: A Communication Perspective on Agentic AI Interfaces
May 2, 2026Eunchae Jang, S. Shyam SundarAgentic Systems Human Oversight
OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder
May 2, 2026Detao Bai, Shimin Yao, Weixuan Chen +4Audio-Visual Reasoning Omni-Modal
InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene
May 1, 2026Chaoyue Xing, Wei Mao, Miaomiao LiuHuman Motion Generation Physics Simulation
Seeking Information with RAG-Assistants: Does Model Size Matter in Human-AI Collaborations?
May 1, 2026Lennard C. Froma, Tom Kouwenhoven, Maaike H. T. de Boer +2Human-Ai Collaboration Large Language Model Performance
Linking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving
May 1, 2026Ashwin George, Lucas Elbert Suryana, Lorenzo Flipse +5Driving Autonomous Driving
High-Speed Vision Improves Zero-Shot Semantic Understanding of Human Actions
May 1, 2026Yongpeng Cao, Yuji YamakawaOpen-Vocabulary Action Recognition Fine-Grained Video Understanding
On the Role of Artificial Intelligence in Human-Machine Symbiosis
May 1, 2026Ching-Chun Chang, Yuchen Guo, Hanrui Wang +2Human-Ai Collaboration Artificial Intelligence Systems
Human-AI Coordination Zones: A Framework for Designing Human-in-the-Loop Experiences with Agentic AI
May 1, 2026James Pierce, Vaiva Kalnikaitė, Siddharth Gupta +1Human-Ai Collaboration Coordination
Mapping the Methodological Space of Classroom Interaction Research: Scale, Duration, and Modality in an Age of AI
Apr 30, 2026Dorottya Demszky, Edith Bouton, Alison Twiner +2Classrooms Methodology
ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss
Apr 30, 2026Jiaying Ying, Heming Du, Kaihao Zhang +2Human Mesh Recovery Legs
Taming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances
Apr 30, 2026Matteo Da Pelo, Alessio Donvito, Claudio Frongia +2Cognitive Science Artificial Intelligence Models
AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments
Apr 30, 2026Jiaju Chen, Jinghua Piao, Xia Xu +4Economies Autoresearch
Robot Learning from Human Videos: A Survey
Apr 30, 2026Junyi Ma, Erhang Zhang, Haoran Yang +4Human-To-Robot Transfer Video Dataset
Knowledge Affordances for Hybrid Human-AI Information Seeking
Apr 30, 2026Irene CelinoHuman-Ai Collaboration Affordances
Leading Across the Spectrum of Human-AI Relationships: A Conceptual Framework for Increasingly Heterogeneous Teams
Apr 30, 2026Alejandro R. JadadHuman-Centered Framework Human-Ai Interaction
A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations
Apr 29, 2026Timothy Flavin, Sandip SenPartially Observable Markov Decision Process Multi-Agent Reinforcement Learning
SnapPose3D: Diffusion-Based Single-Frame 2D-to-3D Lifting of Human Poses
Apr 29, 2026Alessandro Simoni, Riccardo Catalini, Davide Di Nucci +63D Pose Estimator 3D Object Understanding
People-Centred Medical Image Analysis via Fairness-Aware Human-AI Cooperation
Apr 28, 2026Zheng Zhang, Milad Masroor, Cuong Nguyen +6Fairness-Aware Learning Medical Image Classification
Ceci n'est pas une explication: Evaluating Explanation Failures as Explainability Pitfalls in Language Learning Systems
Apr 28, 2026Ben Knight, Wm. Matthew Kennedy, Danielle Carvalho +2Explainability English
A paradox of AI fluency
Apr 28, 2026Christopher Potts, Moritz SudhofFluency Human-Ai Interaction
Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations
Apr 28, 2026Nanxu Gong, Zixin Chen, Haotian Li +5Human-Ai Interaction Theory-Of-Mind Reasoning

May 9, 2026 · cs.AIJ/K move · Enter open · S save

When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees

Dongxin Guo, Jikun Wu, Siu-Ming Yiu

The University of Hong Kong, Hong Kong, China · Stellaris AI Limited, Hong Kong, China · Brain Investing Limited, Hong Kong, China

Human-AI teams fail to outperform their best member in 70% of studies, yet no theory specifies when complementarity is achievable. We derive tight bounds for the broad class of confidence-based aggregation rules by integrating signal detection theory with information-theoretic analysis, yielding four results: (1) a complementarity theorem (teams outperform individuals iff error correlation

ρ_{HM} < ρ^*

, with

ρ^* \approx a

in the symmetric near-chance regime); (2) minimax bounds showing gains scale as

Θ(\sqrt{Δd})

with metacognitive sensitivity difference; (3) an impossibility result proving no confidence-based aggregation rule achieves complementarity when

ρ_{HM} \geq ρ^*

; and (4) multi-class generalization

ρ^*_K \approx ρ^*/\sqrt{K-1}

. Predictions match observed team accuracy (

R = 0.94

on ImageNet-16H,

R = 0.91

on CIFAR-10H) and the multi-class threshold scaling holds on human data (

R = 0.93

K = 16

), with robustness under non-Gaussian distributions. The framework explains why complementarity is rare and provides actionable design formulas; results apply to aggregation, not to interactive deliberation that generates novel answers.

Human-Ai Collaboration Impossibility Metacognition Minimax

Open paper Ask about it PDF